CN117133283A - A voice wake-up circuit, method and electronic device - Google Patents

Abstract

The application discloses a voice awakening circuit, a voice awakening method and electronic equipment, relates to the field of voice awakening, and is used for realizing a voice awakening function with low power consumption when the electronic equipment is in a standby state. The circuit comprises: the device comprises a high-power-consumption first processor, a low-power-consumption second processor, a switch circuit, a voltage reduction circuit and an audio acquisition module for acquiring audio data. The switch circuit is respectively coupled to the first processor, the power end and the voltage reducing circuit; the step-down circuit is also coupled to the audio acquisition module. When the electronic equipment is in a standby state, the first processor is used for controlling the switching circuit to be conducted, enabling the power supply end to supply power to the audio acquisition module through the switching circuit and the voltage reduction circuit, and indicating the second processor to enter a dormant state after detecting whether the audio data comprise wake-up words or not; if the wake-up word is detected, the second processor is used for waking up the first processor; the first processor is further configured to perform speech recognition on the audio data, thereby performing a corresponding operation.

Description

Translated fromChinese

一种语音唤醒电路、方法和电子设备A voice wake-up circuit, method and electronic device

技术领域Technical field

本申请涉及语音唤醒领域，尤其涉及一种语音唤醒电路、方法和电子设备。The present application relates to the field of voice wake-up, and in particular to a voice wake-up circuit, method and electronic device.

背景技术Background technique

通过语音唤醒技术，可以在不直接操控电子设备的情况下唤醒电子设备。通常，为了确保通过语音唤醒技术随时唤醒电子设备，电子设备的处理器需要持续运行语音唤醒算法，并且在通过语音唤醒技术操控电子设备时，电子设备需要处于熄屏或亮屏等非待机状态。Through voice wake-up technology, electronic devices can be woken up without directly controlling the electronic device. Generally, in order to ensure that the electronic device can be woken up at any time through voice wake-up technology, the processor of the electronic device needs to continuously run the voice wake-up algorithm, and when the electronic device is controlled through voice wake-up technology, the electronic device needs to be in a non-standby state such as turning off the screen or turning on the screen.

但是，如果电子设备处于待机状态，则无法通过语音唤醒技术操控电子设备；如果电子设备处于熄屏或亮屏等非待机状态，电子设备的处理器需要持续运行语音唤醒算法，这样，不但会占用处理器的资源，导致电子设备的性能下降，而且会增加电子设备的功耗。However, if the electronic device is in a standby state, it cannot be controlled through voice wake-up technology; if the electronic device is in a non-standby state such as turning off the screen or turning on the screen, the processor of the electronic device needs to continue to run the voice wake-up algorithm, which will not only occupy The resources of the processor cause the performance of the electronic device to decrease and increase the power consumption of the electronic device.

发明内容Contents of the invention

本申请提供一种语音唤醒电路、方法和电子设备，用于在电子设备处于待机状态时能够低功耗的实现语音唤醒功能。This application provides a voice wake-up circuit, method and electronic device, which are used to realize the voice wake-up function with low power consumption when the electronic device is in a standby state.

为达到上述目的，本申请采用如下技术方案：In order to achieve the above purpose, this application adopts the following technical solutions:

第一方面，提供了一种语音唤醒电路，应用于电子设备，该电路包括：高功耗的第一处理器、低功耗的第二处理器、开关电路、降压电路，以及用于采集音频数据的音频采集模块。开关电路的第一端耦合至第一处理器，开关电路的第二端用于耦合至电源端，开关电路的第三端耦合至降压电路的第一端；降压电路的第二端耦合至音频采集模块。In the first aspect, a voice wake-up circuit is provided for use in electronic equipment. The circuit includes: a high-power first processor, a low-power second processor, a switch circuit, a voltage-reducing circuit, and a collection device. Audio collection module for audio data. The first end of the switching circuit is coupled to the first processor, the second end of the switching circuit is coupled to the power end, the third end of the switching circuit is coupled to the first end of the buck circuit; the second end of the buck circuit is coupled to the audio collection module.

当电子设备处于待机状态时，第一处理器用于控制开关电路导通，以使电源端通过开关电路向降压电路提供目标电压，降压电路用于对目标电压降压后向音频采集模块供电，以及，指示第二处理器检测音频数据中是否包括唤醒词之后进入休眠状态。如果第二处理器检测到唤醒词，则第二处理器用于唤醒第一处理器；第一处理器还用于对音频数据进行语音识别，以执行对应的操作。When the electronic device is in a standby state, the first processor is used to control the switch circuit to conduct, so that the power supply terminal provides the target voltage to the buck circuit through the switch circuit, and the buck circuit is used to step down the target voltage and then supply power to the audio acquisition module. , and, instruct the second processor to detect whether the audio data includes the wake-up word and then enter the sleep state. If the second processor detects the wake-up word, the second processor is used to wake up the first processor; the first processor is also used to perform speech recognition on the audio data to perform corresponding operations.

采用本申请提供的语音唤醒电路，当电子设备处于待机状态时，第一处理器控制开关电路导通，以使电源端通过开关电路、降压电路向音频采集模块供电。这样，当电子设备处于待机状态时，音频采集模块仍然能够采集音频数据。这为电子设备在待机状态时具有语音唤醒功能提供了硬件基础。同时，功耗较高的第一处理器还在指示功耗较低的第二处理器持续的检测唤醒词之后进入休眠状态。这样，功耗较高的第一处理器不需要检测唤醒词，从而可以降低第一处理器的功耗，还可以提升第一处理器的性能，进而可以降低电子设备的功耗，并且提升电子设备的性能。当第二处理器检测到唤醒词之后唤醒第一处理器，第一处理器对音频数据进行语音识别，从而执行对应的操作。由此可见，申请提供的语音唤醒电路使电子设备处于待机状态时，能够低功耗的实现语音唤醒功能。Using the voice wake-up circuit provided by this application, when the electronic device is in a standby state, the first processor controls the switch circuit to be turned on, so that the power supply terminal supplies power to the audio collection module through the switch circuit and the buck circuit. In this way, when the electronic device is in standby state, the audio collection module can still collect audio data. This provides a hardware foundation for electronic devices to have a voice wake-up function when in standby mode. At the same time, the first processor with higher power consumption also instructs the second processor with lower power consumption to continue detecting the wake-up word and enter the sleep state. In this way, the first processor with higher power consumption does not need to detect the wake-up word, which can reduce the power consumption of the first processor and improve the performance of the first processor, thereby reducing the power consumption of the electronic device and improving the efficiency of the electronic device. Equipment performance. When the second processor detects the wake-up word and wakes up the first processor, the first processor performs speech recognition on the audio data to perform corresponding operations. It can be seen that the voice wake-up circuit provided in the application can realize the voice wake-up function with low power consumption when the electronic device is in standby state.

在一种可能的实施方式中，上述第一处理器用于指示第二处理器检测音频数据中是否包括唤醒词，具体包括：第一处理器获取电子设备的当前功耗；如果电子设备的当前功耗小于目标功耗，则第一处理器指示第二处理器检测音频数据中是否包括唤醒词。这样，能够进一步确保电子设备在处于待机状态时能够低功耗的实现语音唤醒功能。In a possible implementation, the above-mentioned first processor is used to instruct the second processor to detect whether the audio data includes a wake-up word, which specifically includes: the first processor obtains the current power consumption of the electronic device; if the current power consumption of the electronic device If the power consumption is less than the target power consumption, the first processor instructs the second processor to detect whether the audio data includes the wake-up word. In this way, it can further ensure that the electronic device can realize the voice wake-up function with low power consumption when it is in the standby state.

在一种可能的实施方式中，当所述电子设备处于熄屏状态，并且电子设备无音频音箱业务时，上述第一处理器还用于控制电子设备从熄屏状态切换至待机状态。In a possible implementation, when the electronic device is in the screen-off state and the electronic device has no audio speaker service, the first processor is further configured to control the electronic device to switch from the screen-off state to the standby state.

电子设备处于熄屏状态，并且电子设备无音频音箱业务，相当于，电子设备既没有播放视频节目，也没有播放音频节目。此时，第一处理器控制电子设备从熄屏状态切换到待机状态，使电子设备中的大部分模块下电，可以极大地降低电子设备的功耗，并且使电子设备仍然具有语音唤醒功能。The electronic device is in the screen-off state, and the electronic device does not have audio speaker services. This is equivalent to the electronic device playing neither video programs nor audio programs. At this time, the first processor controls the electronic device to switch from the screen-off state to the standby state, powering off most of the modules in the electronic device, which can greatly reduce the power consumption of the electronic device and enable the electronic device to still have the voice wake-up function.

在一种可能的实施方式中，当电子设备处于亮屏状态时，上述第一处理器还用于指示第二处理器检测音频数据中是否包括唤醒词。In a possible implementation, when the electronic device is in the screen-on state, the first processor is further configured to instruct the second processor to detect whether the audio data includes a wake-up word.

在电子设备处于亮屏状态时，由低功耗的第二处理器检测唤醒词。也就是说，在电子设备处于亮屏状态时，检测唤醒词(即语音侦测)是由低功耗的第二处理器来完成的。这样，第一处理器不用检测唤醒词，降低了第一处理器的功耗，从而使电子设备在处于亮屏状态时能够低功耗的实现语音唤醒功能。When the electronic device is in the screen-on state, the low-power second processor detects the wake-up word. That is to say, when the electronic device is in the screen-on state, detecting the wake-up word (ie, voice detection) is completed by the low-power second processor. In this way, the first processor does not need to detect the wake-up word, which reduces the power consumption of the first processor, so that the electronic device can implement the voice wake-up function with low power consumption when the screen is on.

在一种可能的实施方式中，上述开关电路包括：第一开关子电路和第二开关子电路。第一开关子电路的第一端耦合至第一处理器，第一开关子电路的第二端用于耦合至电源端，第一开关子电路的第三端耦合至第二开关子电路的第一端。第二开关子电路的第二端用于耦合至电源端，第二开关子电路的第三端耦合至降压电路。当电子设备处于待机状态时，第一处理器用于，控制第一开关子电路导通，以使第二开关子电路导通，电源端通过第二开关子电路向降压电路提供目标电压。In a possible implementation, the above-mentioned switch circuit includes: a first switch sub-circuit and a second switch sub-circuit. A first terminal of the first switch sub-circuit is coupled to the first processor, a second terminal of the first switch sub-circuit is coupled to the power supply terminal, and a third terminal of the first switch sub-circuit is coupled to a third terminal of the second switch sub-circuit. One end. The second terminal of the second switch sub-circuit is coupled to the power terminal, and the third terminal of the second switch sub-circuit is coupled to the buck circuit. When the electronic device is in a standby state, the first processor is used to control the first switch subcircuit to turn on so that the second switch subcircuit turns on, and the power supply terminal provides the target voltage to the buck circuit through the second switch subcircuit.

在一种可能的实施方式中，上述第一开关子电路包括：第一电阻、第二电阻、NPN型三极管和第三电阻。第一电阻的第一端为第一开关子电路的第一端，第一电阻的第二端为第一开关子电路的第二端。第二电阻的第一端耦合至第一电阻的第一端，第二电阻的第二端耦合至NPN型三极管的基极。NPN型三极管的发射极用于耦合至接地端，NPN型三极管的集电极耦合至第三电阻的第一端。第三电阻的第二端为第一开关子电路的第三端。第一处理器具体用于：当电子设备处于待机状态时，提供高电平，从而控制NPN型三极管导通。In a possible implementation, the above-mentioned first switch sub-circuit includes: a first resistor, a second resistor, an NPN transistor and a third resistor. The first end of the first resistor is the first end of the first switch sub-circuit, and the second end of the first resistor is the second end of the first switch sub-circuit. The first terminal of the second resistor is coupled to the first terminal of the first resistor, and the second terminal of the second resistor is coupled to the base of the NPN transistor. The emitter of the NPN transistor is coupled to the ground terminal, and the collector of the NPN transistor is coupled to the first terminal of the third resistor. The second terminal of the third resistor is the third terminal of the first switch sub-circuit. The first processor is specifically used to provide a high level when the electronic device is in a standby state, thereby controlling the conduction of the NPN transistor.

在一种可能的实施方式中，上述第二开关子电路包括：第四电阻和P型场效应管。第四电阻的第一端为第二开关子电路的第一端，第四电阻的第二端为第二开关子电路的第二端。P型场效应管的栅极耦合至所述第四电阻的第一端，P型场效应管的源极耦合至第四电阻的第二端，P型场效应管的漏极耦合至降压电路。In a possible implementation, the above-mentioned second switch sub-circuit includes: a fourth resistor and a P-type field effect transistor. The first end of the fourth resistor is the first end of the second switch sub-circuit, and the second end of the fourth resistor is the second end of the second switch sub-circuit. The gate of the P-type field effect transistor is coupled to the first end of the fourth resistor, the source of the P-type field effect transistor is coupled to the second end of the fourth resistor, and the drain of the P-type field effect transistor is coupled to the buck circuit.

通常，处理器的通用输入输出(general-purpose input/output，GPIO)接口输出的电压无法驱动功率较大的场效应管。因此，本申请中，第一处理器通过驱动NPN型三极管后，再通过第三电阻和第四电阻对电源端的电压进行分压后，使P型场效应管的源极的电压、栅极的电压满足导通条件，以此来驱动P型场效应管。Usually, the voltage output by the processor's general-purpose input/output (GPIO) interface cannot drive a relatively powerful field effect transistor. Therefore, in this application, after the first processor drives the NPN transistor, and then divides the voltage at the power supply terminal through the third resistor and the fourth resistor, the voltage of the source of the P-type field effect transistor and the voltage of the gate are The voltage meets the conduction condition to drive the P-type field effect transistor.

在一种可能的实施方式中，上述开关电路可以包括第三开关子电路。第三开关子电路的第一端耦合至第一处理器，第三开关子电路的第二端耦合至电源端，第三开关子电路的第三端耦合至降压电路的第一端。第一处理器具体用于，当电子设备处于待机状态时，控制第三开关子电路导通，电源端向降压电路提供目标电压。In a possible implementation, the above-mentioned switch circuit may include a third switch sub-circuit. The first terminal of the third switch sub-circuit is coupled to the first processor, the second terminal of the third switch sub-circuit is coupled to the power terminal, and the third terminal of the third switch sub-circuit is coupled to the first terminal of the buck circuit. The first processor is specifically used to control the third switch sub-circuit to turn on when the electronic device is in a standby state, and the power supply terminal provides the target voltage to the buck circuit.

在一种可能的实施方式中，上述第三开关子电路包括：第十电阻、第十一电阻和NPN型三极管。第十电阻的第一端为第三开关子电路的第一端，第十电阻的第二端为第三开关子电路的第二端。第十一电阻的第一端耦合至第十电阻的第一端，第十一电阻的第二端耦合至NPN型三极管的基极。NPN型三极管的发射极用于耦合至接地端，NPN型三极管的集电极为第三开关子电路的第三端。所述降压电路的第三端耦合至所述电源端。第一处理器具体用于：当电子设备处于待机状态时，控制NPN型三极管导通。In a possible implementation, the above-mentioned third switch sub-circuit includes: a tenth resistor, an eleventh resistor and an NPN transistor. The first end of the tenth resistor is the first end of the third switch sub-circuit, and the second end of the tenth resistor is the second end of the third switch sub-circuit. The first terminal of the eleventh resistor is coupled to the first terminal of the tenth resistor, and the second terminal of the eleventh resistor is coupled to the base of the NPN transistor. The emitter of the NPN transistor is used to couple to the ground terminal, and the collector of the NPN transistor is the third terminal of the third switch subcircuit. The third terminal of the buck circuit is coupled to the power terminal. The first processor is specifically used to control the NPN transistor to conduct when the electronic device is in a standby state.

当电子设备处于待机状态时，第一处理器的GPIO接口可以输出高电平的电压(如3.3V)。此时，第一处理器的GPIO接口还可以输出目标电流(如0.4mA)。这样，流过NPN型三极管的基极的电流可以包括：目标电流，流过第十电阻的电流，以及流过第十一电阻的电流。通常，这三部分电流的总和可以满足NPN型三极管的导通条件。因此，NPN型三极管可以导通，使得电源端向降压电路供电。When the electronic device is in a standby state, the GPIO interface of the first processor can output a high-level voltage (such as 3.3V). At this time, the GPIO interface of the first processor can also output the target current (such as 0.4mA). In this way, the current flowing through the base of the NPN transistor may include: the target current, the current flowing through the tenth resistor, and the current flowing through the eleventh resistor. Usually, the sum of these three parts of current can meet the conduction conditions of the NPN transistor. Therefore, the NPN transistor can be turned on, allowing the power supply terminal to supply power to the buck circuit.

在一种可能的实施方式中，上述第三开关子电路包括：P型场效应管。P型场效应管的栅极耦合至第一处理器，P型场效应管的源极耦合至电源端，P型场效应管的漏极耦合至降压电路的第一端。In a possible implementation, the above-mentioned third switch sub-circuit includes: a P-type field effect transistor. The gate of the P-type field effect transistor is coupled to the first processor, the source of the P-type field effect transistor is coupled to the power terminal, and the drain of the P-type field effect transistor is coupled to the first terminal of the buck circuit.

当电子设备处于待机状态时，第一处理器的GPIO接口可以输出低电平的电压。此时，P型场效应管的栅极的电压，以及源极的电压满足导通条件，以此来驱动P型场效应管，使得P型场效应管导通，电源端通过P型场效应管的源极、漏极向降压电路供电。When the electronic device is in a standby state, the GPIO interface of the first processor can output a low-level voltage. At this time, the voltage of the gate of the P-type field effect transistor and the voltage of the source meet the conduction conditions, thereby driving the P-type field effect transistor, causing the P-type field effect transistor to conduct, and the power supply terminal passes through the P-type field effect transistor. The source and drain of the tube supply power to the buck circuit.

在一种可能的实施方式中，上述降压电路包括：降压器件、第六电阻和第七电阻。降压器件的输入端耦合至开关电路的第三端，降压器件的输出端耦合至第六电阻的第一端、降压器件的接地端，以及音频采集模块，降压器件的调整端耦合至第六电阻的第二端、第七电阻的第一端。第七电阻的第二端用于耦合至接地端。In a possible implementation, the above voltage reducing circuit includes: a voltage reducing device, a sixth resistor and a seventh resistor. The input terminal of the buck device is coupled to the third terminal of the switch circuit, the output terminal of the buck device is coupled to the first terminal of the sixth resistor, the ground terminal of the buck device, and the audio acquisition module, and the adjustment terminal of the buck device is coupled to the second terminal of the sixth resistor and the first terminal of the seventh resistor. The second terminal of the seventh resistor is used for coupling to the ground terminal.

第二方面，提供了一种语音唤醒方法，应用于如第一方面及其任一实施方式所述的语音唤醒电路。该电路包括：第一处理器、第二处理器、开关电路、降压电路和音频采集模块。第一处理器的功耗大于第二处理器的功耗。音频采集模块用于采集音频数据。开关电路的第一端耦合至第一处理器，开关电路的第二端用于耦合至电源端，开关电路的第三端耦合至降压电路的第一端。降压电路的第二端耦合至音频采集模块。电源端通过导通后的开关电路向降压电路提供目标电压，降压电路用于对目标电压降压后向音频采集模块供电。该方法包括：A second aspect provides a voice wake-up method, which is applied to the voice wake-up circuit described in the first aspect and any of its implementation modes. The circuit includes: a first processor, a second processor, a switch circuit, a buck circuit and an audio acquisition module. The power consumption of the first processor is greater than the power consumption of the second processor. The audio collection module is used to collect audio data. The first terminal of the switch circuit is coupled to the first processor, the second terminal of the switch circuit is coupled to the power terminal, and the third terminal of the switch circuit is coupled to the first terminal of the buck circuit. The second terminal of the buck circuit is coupled to the audio acquisition module. The power supply terminal provides the target voltage to the voltage reduction circuit through the switched circuit after being turned on. The voltage reduction circuit is used to reduce the target voltage and then supply power to the audio acquisition module. The method includes:

当电子设备处于待机状态，第一处理器控制开关电路导通，以及，指示第二处理器检测音频数据中是否包括唤醒词之后进入休眠状态；如果第二处理器检测到唤醒词，则第二处理器唤醒第一处理器；第一处理器对音频数据进行语音识别，以执行对应的操作。When the electronic device is in the standby state, the first processor controls the switch circuit to turn on, and instructs the second processor to detect whether the audio data includes a wake-up word and then enter the sleep state; if the second processor detects the wake-up word, the second processor The processor wakes up the first processor; the first processor performs speech recognition on the audio data to perform corresponding operations.

在一种可能的实施方式中，上述第一处理器指示第二处理器检测音频数据中是否包括唤醒词，包括：第一处理器获取电子设备的当前功耗；如果电子设备的当前功耗小于目标功耗，则第一处理器指示第二处理器检测音频数据中是否包括唤醒词。In a possible implementation, the above-mentioned first processor instructs the second processor to detect whether the audio data includes a wake-up word, including: the first processor obtains the current power consumption of the electronic device; if the current power consumption of the electronic device is less than target power consumption, the first processor instructs the second processor to detect whether the audio data includes the wake-up word.

在一种可能的实施方式中，上述方法还包括：当电子设备处于熄屏状态，并且电子设备无音频音箱业务时，第一处理器控制电子设备从熄屏状态切换至待机状态。In a possible implementation, the above method further includes: when the electronic device is in the screen-off state and the electronic device has no audio speaker service, the first processor controls the electronic device to switch from the screen-off state to the standby state.

在一种可能的实施方式中，上述方法还包括：当电子设备处于亮屏状态时，第一处理器指示第二处理器检测音频数据中是否包括唤醒词。In a possible implementation, the above method further includes: when the electronic device is in the screen-on state, the first processor instructs the second processor to detect whether the audio data includes the wake-up word.

第三方面，提供了一种电子设备，包括第一方面及其任一实施方式所述的语音唤醒电路，以及存储器。存储器中存储指令，当语音唤醒电路中的第一处理器和第二处理器执行指令时，如第二方面及其任一实施方式所述的方法被执行。In a third aspect, an electronic device is provided, including the voice wake-up circuit described in the first aspect and any embodiment thereof, and a memory. Instructions are stored in the memory, and when the first processor and the second processor in the voice wake-up circuit execute the instructions, the method described in the second aspect and any embodiment thereof is executed.

第四方面，提供了一种计算机可读存储介质，包括指令，当指令在电子设备上运行时，使得电子设备执行如第二方面及其任一实施方式所述的方法。In a fourth aspect, a computer-readable storage medium is provided, including instructions. When the instructions are run on an electronic device, the electronic device causes the electronic device to perform the method described in the second aspect and any implementation manner thereof.

第五方面，提供了一种包含指令的计算机程序产品，当指令在上述电子设备上运行时，使得该电子设备执行如第二方面及其任一实施方式所述的方法。In a fifth aspect, a computer program product containing instructions is provided. When the instructions are run on the above-mentioned electronic device, the electronic device is caused to execute the method described in the second aspect and any of its implementation modes.

第六方面，提供了一种芯片系统，该芯片系统包括处理器，用于支持电子设备实现上述第二方面中所涉及的功能。在一种可能的设计中，该电子设备还包括接口电路，接口电路可用于从其它装置(例如存储器)接收信号，或者，向其它装置(例如通信接口)发送信号。该芯片系统可以包括芯片，还可以包括其他分立器件。In a sixth aspect, a chip system is provided. The chip system includes a processor and is used to support an electronic device to implement the functions involved in the above second aspect. In a possible design, the electronic device further includes an interface circuit, which can be used to receive signals from other devices (such as a memory) or send signals to other devices (such as a communication interface). The chip system may include chips and may also include other discrete devices.

第二方面至第六方面的技术效果参照第一方面及其任一实施方式的技术效果，在此不再重复。For the technical effects of the second to sixth aspects, refer to the technical effects of the first aspect and any of its implementations, which will not be repeated here.

附图说明Description of the drawings

图1为现有技术中的一种电子设备各状态之间的关系示意图；Figure 1 is a schematic diagram of the relationship between various states of an electronic device in the prior art;

图2为本申请实施例提供的一种语音唤醒的场景示意图；Figure 2 is a schematic diagram of a voice wake-up scenario provided by an embodiment of the present application;

图3为本申请实施例提供的一种电子设备的结构示意图；Figure 3 is a schematic structural diagram of an electronic device provided by an embodiment of the present application;

图4为本申请实施例提供的一种电子设备运行的软件架构示意图；Figure 4 is a schematic diagram of a software architecture running on an electronic device provided by an embodiment of the present application;

图5为本申请实施例提供的一种电子设备的电路结构示意图之一；Figure 5 is a schematic diagram of a circuit structure of an electronic device provided by an embodiment of the present application;

图6为本申请实施例提供的一种电子设备各状态之间的关系示意图之一；Figure 6 is a schematic diagram of the relationship between various states of an electronic device provided by an embodiment of the present application;

图7为本申请实施例提供的一种电子设备各状态之间的关系示意图之二；Figure 7 is a second schematic diagram of the relationship between various states of an electronic device provided by an embodiment of the present application;

图8为本申请实施例提供的一种电子设备的电路结构示意图之二；Figure 8 is a second schematic diagram of the circuit structure of an electronic device provided by an embodiment of the present application;

图9为本申请实施例提供的一种电子设备的电路结构示意图之三；Figure 9 is a third schematic diagram of the circuit structure of an electronic device provided by an embodiment of the present application;

图10为本申请实施例提供的一种电子设备的电路结构示意图之四；Figure 10 is a fourth schematic diagram of the circuit structure of an electronic device provided by an embodiment of the present application;

图11为本申请实施例提供的一种电子设备的电路结构示意图之五；Figure 11 is a fifth schematic diagram of the circuit structure of an electronic device provided by an embodiment of the present application;

图12为本申请实施例提供的一种语音唤醒方法的流程示意图；Figure 12 is a schematic flow chart of a voice wake-up method provided by an embodiment of the present application;

图13为本申请实施例提供的一种芯片系统的结构示意图。Figure 13 is a schematic structural diagram of a chip system provided by an embodiment of the present application.

具体实施方式Detailed ways

首先对本申请涉及的一些概念进行描述。First, some concepts involved in this application are described.

本申请实施例涉及的术语“第一”、“第二”等仅用于区分同一类型特征的目的，不能理解为用于指示相对重要性、数量、顺序等。The terms "first", "second", etc. involved in the embodiments of this application are only used for the purpose of distinguishing features of the same type and cannot be understood as indicating relative importance, quantity, order, etc.

本申请实施例涉及的术语“示例性的”或者“例如”等词用于表示作例子、例证或说明。本申请中被描述为“示例性的”或者“例如”的任何实施例或设计方案不应被解释为比其他实施例或设计方案更优选或更具优势。确切而言，使用“示例性的”或者“例如”等词旨在以具体方式呈现相关概念。The terms “exemplary” or “for example” used in the embodiments of this application are used to represent examples, illustrations or descriptions. Any embodiment or design described herein as "exemplary" or "such as" is not intended to be construed as preferred or advantageous over other embodiments or designs. Rather, use of the words "exemplary" or "such as" is intended to present the concept in a concrete manner.

本申请实施例涉及的术语“耦合”、“连接”应做广义理解，例如，可以指物理上的直接连接，也可以指通过电子器件实现的间接连接，例如通过电阻、电感、电容或其他电子器件实现的连接。The terms "coupling" and "connection" involved in the embodiments of this application should be understood in a broad sense. For example, they may refer to a physical direct connection, or they may refer to an indirect connection realized through electronic devices, such as resistance, inductance, capacitance or other electronic devices. The connection implemented by the device.

语音唤醒技术被广泛应用在电子设备上，通过语音唤醒技术，用户可以在不直接操控电子设备的情况下，通过语音指令操控电子设备。例如，切换电子设备的状态，或者切换电子设备当前播放的节目等。如图1所示，电子设备可以包括：熄屏状态、亮屏状态、待机状态和下电状态。下面结合图1，简单描述电子设备在各个状态之间如何切换。Voice wake-up technology is widely used in electronic devices. Through voice wake-up technology, users can control electronic devices through voice commands without directly controlling the electronic device. For example, switching the status of the electronic device, or switching the program currently played by the electronic device, etc. As shown in Figure 1, the electronic device may include: screen off state, screen on state, standby state and power off state. The following is a brief description of how the electronic device switches between various states in conjunction with Figure 1.

1、电子设备处于熄屏状态时，电子设备中除了显示屏以外(如音频采集模块、音频音箱模块等)的模块处于工作状态。此时，如S1，电子设备可以响应于亮屏语音指令从熄屏状态切换至亮屏状态；或者，电子设备可以响应于用户点击电子设备的开关键(或者与电子设备配套的遥控器的待机键)，从熄屏状态切换至亮屏状态。如S2，当切断电子设备与电源端的连接(如用户拔掉电源)后，电子设备自动的从熄屏状态切换至下电状态。1. When the electronic device is in the screen-off state, the modules in the electronic device other than the display screen (such as audio collection module, audio speaker module, etc.) are in working state. At this time, as in S1, the electronic device can switch from the screen-off state to the screen-on state in response to the voice command to turn on the screen; or, the electronic device can respond to the user clicking the on/off key of the electronic device (or the standby key of the remote control matched with the electronic device). key) to switch from the screen off state to the screen on state. For example, in S2, when the connection between the electronic device and the power supply is cut off (for example, the user unplugs the power supply), the electronic device automatically switches from the screen-off state to the power-off state.

2、电子设备处于亮屏状态时，电子设备的各个模块(如显示屏、音频采集模块、音频音箱模块等)均处于工作状态。此时，电子设备可以响应于业务切换语音指令，切换电子设备正在播放的节目(如音频节目或视频节目)。如S3，电子设备还可以响应于熄屏语音指令从亮屏状态切换至熄屏状态；或者，电子设备可以响应于用户点击与电子设备配套的遥控器的待机键，从亮屏状态切换至熄屏状态；或者，电子设备在预设时间段内没有播放任务时，自动从亮屏状态切换到熄屏状态。如S4，电子设备还可以响应于待机语音指令从亮屏状态切换到待机状态；或者，电子设备可以响应于用户点击电子设备的开关键，从亮屏状态切换到待机状态。如S5，当切断电子设备与电源端的连接(如用户拔掉电源)后，电子设备自动的从亮屏状态切换至下电状态。2. When the electronic device is in the screen-on state, each module of the electronic device (such as the display screen, audio collection module, audio speaker module, etc.) is in working state. At this time, the electronic device can respond to the service switching voice command and switch the program (such as an audio program or a video program) being played by the electronic device. For example, in S3, the electronic device can also switch from the screen-on state to the screen-off state in response to the screen-off voice command; or, the electronic device can switch from the screen-on state to the screen-off state in response to the user clicking the standby button of the remote control matched with the electronic device. screen state; or, when the electronic device does not play a task within a preset time period, it automatically switches from the screen on state to the screen off state. Like S4, the electronic device can also switch from the screen-on state to the standby state in response to the standby voice command; or, the electronic device can switch from the screen-on state to the standby state in response to the user clicking the on/off key of the electronic device. For example, S5, when the connection between the electronic device and the power supply is cut off (for example, the user unplugs the power supply), the electronic device automatically switches from the screen-on state to the power-off state.

示例性的，假设电子设备为智能语音电视机，以通过业务切换语音指令切换电子设备正在播放视频节目为例。如图2中A所示，智能语音电视机播放第一频道的节目。当智能语音电视机检测到唤醒词(如你好，小B)时，如图2中B所示，智能语音电视机发出反馈信息(如请讲)。如图2中C和D所示，当智能语音电视机检测到具体的语音指令(如切换到第二频道)时，智能语音电视机根据该语音指令执行对应的操作(如从播放第一频道的节目切换至播放第二频道的节目)。For example, assuming that the electronic device is a smart voice television, taking the video program being played by the electronic device to be switched through a service switching voice command as an example. As shown in A in Figure 2, the smart voice TV plays the program of the first channel. When the smart voice TV detects the wake-up word (such as hello, little B), as shown in B in Figure 2, the smart voice TV sends feedback information (such as please speak). As shown in C and D in Figure 2, when the smart voice TV detects a specific voice command (such as switching to the second channel), the smart voice TV performs the corresponding operation according to the voice command (such as playing the first channel from switch the program to the program on channel 2).

3、电子设备处于待机状态时，电子设备中大部分模块(如音频采集模块、音频音箱模块、显示屏等)停止工作。在待机状态下，电子设备的功耗小于预设功耗(如0.5W)。此时，由于电子设备的音频采集模块已停止工作，因此，电子设备无法采集音频数据，那么，电子设备无法响应于亮屏语音指令从待机状态切换至亮屏状态。但是，如S6，电子设备可以响应于用户点击电子设备的开关键(或者与电子设备配套的遥控器的待机键)，从待机状态切换到亮屏状态。也就是说，在待机状态下，电子设备不具有语音唤醒功能。如S7，当切断电子设备与电源端的连接(如用户拔掉电源)后，电子设备从待机状态切换至下电状态。3. When the electronic device is in standby mode, most modules in the electronic device (such as audio collection module, audio speaker module, display screen, etc.) stop working. In the standby state, the power consumption of the electronic device is less than the preset power consumption (such as 0.5W). At this time, since the audio collection module of the electronic device has stopped working, the electronic device cannot collect audio data. Therefore, the electronic device cannot switch from the standby state to the screen-on state in response to the screen-on voice command. However, like the S6, the electronic device can switch from the standby state to the bright screen state in response to the user clicking the on/off key of the electronic device (or the standby key of the remote control matched with the electronic device). That is to say, in the standby state, the electronic device does not have the voice wake-up function. For example, S7, when the connection between the electronic device and the power supply is cut off (for example, the user unplugs the power supply), the electronic device switches from the standby state to the power-off state.

4、电子设备处于下电状态时，电子设备的各个模块由于无电压输入而停止工作。此时，如S8，将电子设备与电源端连接(如用户插上电源)后，电子设备响应于用户点击电子设备的开关键，以及用户点击与电子设备配套的遥控器的待机键，从下电状态切换至亮屏状态。4. When the electronic equipment is powered off, each module of the electronic equipment stops working due to no voltage input. At this time, like S8, after the electronic device is connected to the power supply (for example, the user plugs in the power), the electronic device responds to the user clicking the on/off key of the electronic device, and the user clicking the standby key of the remote control matched with the electronic device. Switch the power status to the bright screen status.

结合上述过程，在电子设备处于亮屏状态或熄屏状态时，为了确保电子设备能够随时响应于语音唤醒指令执行对应的操作，电子设备的处理器需要持续检测语音唤醒指令，当检测到语音唤醒指令时，再执行对应的操作。这就需要处理器持续地运行语音唤醒算法，不但会占用处理器的资源，导致处理器的性能下降，进而导致电子设备的性能下降，而且会增加处理器的功耗，进而增加电子设备的功耗。当电子设备处于待机状态时，由于音频采集模块无法采集音频数据，因此电子设备在待机状态下不具有语音唤醒功能，而是需要通过手动操作使电子设备在不同状态之间进行切换。这样，降低了用户的使用体验。Combined with the above process, in order to ensure that the electronic device can respond to the voice wake-up command to perform corresponding operations at any time when the electronic device is in the screen-on state or the screen-off state, the processor of the electronic device needs to continuously detect the voice wake-up command. When the voice wake-up is detected command, then perform the corresponding operation. This requires the processor to continuously run the voice wake-up algorithm, which will not only occupy the resources of the processor, leading to a decrease in the performance of the processor, and thus the performance of the electronic device, but also increase the power consumption of the processor, thereby increasing the power of the electronic device. Consumption. When the electronic device is in the standby state, since the audio acquisition module cannot collect audio data, the electronic device does not have a voice wake-up function in the standby state. Instead, the electronic device needs to be manually operated to switch between different states. In this way, the user experience is reduced.

基于上述问题，本申请实施例提供了一种电子设备，当该电子设备处于待机状态时，该电子设备的音频采集模块仍然能够采集音频数据，同时，该电子设备通过低功耗的第二处理器持续的检测音频数据中是否包括唤醒词，一旦检测到唤醒词，第二处理器再唤醒高功耗的第一处理器再对音频数据进行语音识别，从而执行对应的操作。也就是说，高功耗的第一处理器不用持续地检测唤醒词，也不用持续地进行语音识别，这样可以降低第一处理器的功耗，从而使电子设备在待机状态下能够低功耗的实现语音唤醒功能，并且可以提升第一处理器的性能。当该电子设备处于熄屏状态，并且无音频音箱业务时，第一处理器控制电子设备从熄屏状态切换至待机状态，这样极大地降低了电子设备的功耗。当电子设备处于亮屏状态时，首先由第一处理器检测音频数据中是否包括唤醒词，如果未检测到唤醒词，则第一处理器指示第二处理器继续检测唤醒词。如果第二处理器检测到唤醒词，则再唤醒第一处理器对音频数据进行语音识别。也就是说，本申请实施例提供的电子设备处于亮屏状态时也能够低功耗的实现语音唤醒功能。由此可见，本申请实施例提供的电子设备，在熄屏状态、亮屏状态和待机状态下，都能够低功耗的实现语音唤醒功能。Based on the above problems, embodiments of the present application provide an electronic device. When the electronic device is in a standby state, the audio collection module of the electronic device can still collect audio data. At the same time, the electronic device uses a low-power second process to The processor continuously detects whether the audio data includes a wake-up word. Once the wake-up word is detected, the second processor wakes up the high-power first processor and performs speech recognition on the audio data to perform corresponding operations. That is to say, the high-power first processor does not need to continuously detect wake-up words or perform voice recognition. This can reduce the power consumption of the first processor, thereby enabling the electronic device to consume low power in the standby state. It realizes the voice wake-up function and can improve the performance of the first processor. When the electronic device is in the screen-off state and there is no audio speaker service, the first processor controls the electronic device to switch from the screen-off state to the standby state, which greatly reduces the power consumption of the electronic device. When the electronic device is in the screen-on state, the first processor first detects whether the audio data includes the wake-up word. If the wake-up word is not detected, the first processor instructs the second processor to continue detecting the wake-up word. If the second processor detects the wake-up word, it wakes up the first processor to perform speech recognition on the audio data. That is to say, the electronic device provided by the embodiment of the present application can also implement the voice wake-up function with low power consumption when the screen is on. It can be seen that the electronic device provided by the embodiment of the present application can realize the voice wake-up function with low power consumption in the screen off state, screen on state and standby state.

本申请实施例涉及的电子设备可以是一种具有语音唤醒功能的设备，电子设备可以是移动的，也可以是固定的。电子设备可以部署在陆地上(例如室内或室外、手持或车载等)，也可以部署在水面上(例如轮船等)，还可以部署在空中(例如飞机、气球等)。该电子设备可以称为用户设备(user equipment，UE)、接入终端、终端单元、用户单元(subscriberunit)、终端站、移动站(mobile station，MS)、移动台、终端代理或终端装置等。例如，该电子设备可以是智能语音电视机、智能对话玩具、智能音箱等。本申请实施例对电子设备的具体类型和结构等不作限定。下面对电子设备的一种可能结构进行说明。The electronic device involved in the embodiment of the present application may be a device with a voice wake-up function, and the electronic device may be mobile or fixed. Electronic devices can be deployed on land (such as indoor or outdoor, handheld or vehicle-mounted, etc.), on water (such as ships, etc.), or in the air (such as airplanes, balloons, etc.). The electronic equipment may be called user equipment (UE), access terminal, terminal unit, subscriber unit (subscriberunit), terminal station, mobile station (MS), mobile station, terminal agent or terminal device, etc. For example, the electronic device can be a smart voice TV, a smart conversation toy, a smart speaker, etc. The embodiments of the present application do not limit the specific type and structure of the electronic device. A possible structure of the electronic device is described below.

示例性的，以电子设备为智能语音电视机为例，图3示出了电子设备300的一种可能的结构。该电子设备300可以包括：第一处理器311、第二处理器312、存储器320、通信接口330、电源管理模块340、天线、无线通信模块350、音频模块360、扬声器360A、受话器360B、音频采集模块360C、传感器模块370、按键380、指示器390、显示屏391等。For example, taking the electronic device as a smart voice television, FIG. 3 shows a possible structure of the electronic device 300 . The electronic device 300 may include: a first processor 311, a second processor 312, a memory 320, a communication interface 330, a power management module 340, an antenna, a wireless communication module 350, an audio module 360, a speaker 360A, a receiver 360B, and audio collection. Module 360C, sensor module 370, button 380, indicator 390, display screen 391, etc.

其中，传感器模块370可以包括红外传感器、温度传感器、湿度传感器、环境光传感器、距离传感器，但不仅限于此，本申请实施例对此不作限定。The sensor module 370 may include an infrared sensor, a temperature sensor, a humidity sensor, an ambient light sensor, and a distance sensor, but is not limited thereto, and is not limited in this embodiment of the present application.

可以理解的是，本发明实施例示意的结构并不构成对电子设备300的具体限定。在本申请另一些实施例中，电子设备300可以包括比图示更多或更少的部件，或者组合某些部件，或者拆分某些部件，或者不同的部件布置。图示的部件可以以硬件，软件或软件和硬件的组合实现。It can be understood that the structure illustrated in the embodiment of the present invention does not constitute a specific limitation on the electronic device 300 . In other embodiments of the present application, the electronic device 300 may include more or fewer components than shown in the figures, or some components may be combined, some components may be separated, or some components may be arranged differently. The components illustrated may be implemented in hardware, software, or a combination of software and hardware.

第一处理器311可以包括一个或多个处理单元。例如：第一处理器311可以包括应用处理器(application processor，AP)、网络处理器(network processor，NP)、数字信号处理器(digital signal processor，DSP)、微控制单元(micro controller unit，MCU)、可编程逻辑器件(programmable logic device，PLD)、调制解调处理器、图形处理器(graphics processing unit，GPU)、图像信号处理器(image signal processor，ISP)、控制器、视频编解码器、基带处理器以及神经网络处理器(neural-network processingunit，NPU)等。其中，不同的处理单元可以是独立的器件，也可以集成在一个或多个第一处理器中。在一些实施例中，第一处理器311可以是精简指令(advanced RISC machines，ARM)的处理器。The first processor 311 may include one or more processing units. For example, the first processor 311 may include an application processor (AP), a network processor (NP), a digital signal processor (DSP), a micro controller unit (MCU). ), programmable logic device (PLD), modem processor, graphics processing unit (GPU), image signal processor (ISP), controller, video codec , baseband processor and neural network processor (neural-network processing unit, NPU), etc. The different processing units may be independent devices or integrated into one or more first processors. In some embodiments, the first processor 311 may be a processor of advanced RISC machines (ARM).

其中，控制器可以是电子设备300的神经中枢和指挥中心。控制器可以根据指令操作码和时序信号，产生操作控制信号，完成取指令和执行指令的控制。The controller may be the nerve center and command center of the electronic device 300 . The controller can generate operation control signals based on the instruction operation code and timing signals to complete the control of fetching and executing instructions.

第一处理器311中还可以设置存储器，用于存储指令和数据。在一些实施例中，第一处理器311中的存储器为高速缓冲存储器。该存储器可以保存第一处理器311刚用过或循环使用的指令或数据。如果第一处理器311需要再次使用该指令或数据，可从所述存储器中直接调用。避免了重复存取，减少了第一处理器311的等待时间，因而提高了系统的效率。The first processor 311 may also be provided with a memory for storing instructions and data. In some embodiments, the memory in first processor 311 is a cache memory. The memory can store instructions or data that have just been used or recycled by the first processor 311 . If the first processor 311 needs to use the instruction or data again, it can be directly called from the memory. Repeated access is avoided and the waiting time of the first processor 311 is reduced, thus improving the efficiency of the system.

在一些实施例中，第一处理器311可以包括一个或多个接口。接口可以包括集成电路(inter-integrated circuit，I2C)接口、集成电路内置音频(inter-integratedcircuit sound，I2S)接口、脉冲编码调制(pulse code modulation，PCM)接口、通用异步收发传输器(universal asynchronous receiver/transmitter，UART)接口、移动产业处理器接口(mobile industry processor interface，MIPI)、通用输入输出(general-purposeinput/output，GPIO)接口、用户标识模块(subscriber identity module，SIM)接口和/或USB接口等。In some embodiments, first processor 311 may include one or more interfaces. The interface may include an integrated circuit (inter-integrated circuit, I2C) interface, an integrated circuit built-in audio (inter-integrated circuit sound, I2S) interface, a pulse code modulation (PCM) interface, or a universal asynchronous receiver (universal asynchronous receiver) /transmitter, UART) interface, mobile industry processor interface (MIPI), general-purpose input/output (GPIO) interface, subscriber identity module (subscriber identity module, SIM) interface and/or USB Interface etc.

可以理解的是，本申请实施例示意的各模块间的接口连接关系，只是示意性说明，并不构成对电子设备300的结构限定。在本申请另一些实施例中，电子设备300也可以采用上述实施例中不同的接口连接方式，或多种接口连接方式的组合。It can be understood that the interface connection relationship between the modules illustrated in the embodiment of the present application is only a schematic illustration and does not constitute a structural limitation of the electronic device 300 . In other embodiments of the present application, the electronic device 300 may also adopt different interface connection methods in the above embodiments, or a combination of multiple interface connection methods.

第二处理器312可以是相对于第一处理器311来说，功耗更低(通常，第二处理器的功耗可以忽略不计)，且功能和配置更加简单的处理器。在一些实施例中，第二处理器312可以是低功耗的数字信号处理器(digital signal processor，DSP)。第二处理器312可以用于检测音频采集模块采集到的音频数据中是否包括唤醒词(即进行语音侦测)。The second processor 312 may be a processor that consumes lower power than the first processor 311 (generally, the power consumption of the second processor is negligible) and has simpler functions and configurations. In some embodiments, the second processor 312 may be a low-power digital signal processor (DSP). The second processor 312 may be used to detect whether the audio data collected by the audio collection module includes the wake-up word (ie, perform voice detection).

可以理解的是，第二处理器312可以和第一处理器311集成在一起，或者，第二处理器312与第一处理器311可以是独立的器件，本申请实施例对此不作限定。It can be understood that the second processor 312 can be integrated with the first processor 311, or the second processor 312 and the first processor 311 can be independent devices, which is not limited in the embodiment of the present application.

电源管理模块340用于从充电器接收充电输入。其中，充电器可以是是有线充电器。例如，电源管理模块340可以通过充电接口接收有线充电器的充电输入，为第一处理器311、第二处理器312、存储器320、无线通信模块350、音频模块360、传感器模块370、显示屏391、指示器390等供电。在其他一些实施例中，电源管理模块340也可以设置于第一处理器311中。The power management module 340 is used to receive charging input from the charger. The charger may be a wired charger. For example, the power management module 340 can receive the charging input of the wired charger through the charging interface, which is the first processor 311, the second processor 312, the memory 320, the wireless communication module 350, the audio module 360, the sensor module 370, and the display screen 391. , indicator 390 and other power supplies. In some other embodiments, the power management module 340 may also be provided in the first processor 311.

电子设备300的无线通信功能可以通过天线、无线通信模块350、调制解调处理器以及基带处理器等实现。The wireless communication function of the electronic device 300 can be implemented through an antenna, a wireless communication module 350, a modem processor, a baseband processor, and the like.

天线用于发射和接收电磁波信号。电子设备300中的每个天线可用于覆盖单个或多个通信频带。不同的天线还可以复用，以提高天线的利用率。例如：可以将天线复用为无线局域网的分集天线。在另外一些实施例中，天线可以和调谐开关结合使用。Antennas are used to transmit and receive electromagnetic wave signals. Each antenna in electronic device 300 may be used to cover a single or multiple communication frequency bands. Different antennas can also be reused to improve antenna utilization. For example: the antenna can be reused as a diversity antenna for a wireless LAN. In other embodiments, antennas may be used in conjunction with tuning switches.

电子设备300通过GPU、显示屏391以及应用处理器等实现显示功能。GPU为图像处理的微处理器，连接显示屏391和应用处理器。GPU用于执行数学和几何计算，用于图形渲染。处理器210可包括一个或多个GPU，其执行程序指令以生成或改变显示信息。The electronic device 300 implements display functions through a GPU, a display screen 391, an application processor, and the like. The GPU is an image processing microprocessor and is connected to the display screen 391 and the application processor. GPUs are used to perform mathematical and geometric calculations for graphics rendering. Processor 210 may include one or more GPUs that execute program instructions to generate or alter display information.

显示屏391用于显示图像，视频等。显示屏391包括显示面板。在一些实施例中，电子设备300可以包括1个或N个显示屏391，N为大于1的正整数。The display screen 391 is used to display images, videos, etc. The display screen 391 includes a display panel. In some embodiments, the electronic device 300 may include 1 or N display screens 391, where N is a positive integer greater than 1.

存储器320可以用于存储计算机可执行程序代码，所述可执行程序代码包括指令。第一处理器311和第二处理器312通过运行存储在存储器320的指令，从而执行电子设备300的各种功能应用以及数据处理。此外，存储器320可以包括高速随机存取存储器，还可以包括非易失性存储器，例如至少一个磁盘存储器件、闪存器件、通用闪存存储器(universalflash storage，UFS)等。Memory 320 may be used to store computer executable program code, which includes instructions. The first processor 311 and the second processor 312 execute various functional applications and data processing of the electronic device 300 by executing instructions stored in the memory 320 . In addition, the memory 320 may include high-speed random access memory, and may also include non-volatile memory, such as at least one disk storage device, flash memory device, universal flash storage (UFS), etc.

本申请实施例涉及的存储器可以是易失性存储器或非易失性存储器，或可包括易失性和非易失性存储器两者。其中，非易失性存储器可以是只读存储器(read-onlymemory，ROM)、可编程只读存储器(programmable ROM，PROM)、可擦除可编程只读存储器(erasable PROM，EPROM)、电可擦除可编程只读存储器(electrically EPROM，EEPROM)或闪存。易失性存储器可以是随机存取存储器(random access memory，RAM)，其用作外部高速缓存。通过示例性但不是限制性说明，许多形式的RAM可用，例如静态随机存取存储器(static RAM，SRAM)、动态随机存取存储器(dynamic RAM，DRAM)、同步动态随机存取存储器(synchronous DRAM，SDRAM)、双倍数据速率同步动态随机存取存储器(double data rateSDRAM，DDR SDRAM)、增强型同步动态随机存取存储器(enhanced SDRAM，ESDRAM)、同步连接动态随机存取存储器(synchlink DRAM，SLDRAM)和直接内存总线随机存取存储器(directrambus RAM，DR RAM)。应注意，本文描述的系统和方法的存储器旨在包括但不限于这些和任意其它适合类型的存储器。The memory involved in the embodiments of the present application may be a volatile memory or a non-volatile memory, or may include both volatile and non-volatile memories. Among them, the non-volatile memory can be read-only memory (ROM), programmable ROM (PROM), erasable programmable read-only memory (erasable PROM, EPROM), electrically erasable memory Except programmable read-only memory (electrically EPROM, EEPROM) or flash memory. Volatile memory may be random access memory (RAM), which is used as an external cache. By way of illustration, but not limitation, many forms of RAM are available, such as static random access memory (SRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (synchronous DRAM, SDRAM), double data rate synchronous dynamic random access memory (double data rate SDRAM, DDR SDRAM), enhanced synchronous dynamic random access memory (enhanced SDRAM, ESDRAM), synchronous link dynamic random access memory (synchlink DRAM, SLDRAM) and direct memory bus random access memory (directrambus RAM, DR RAM). It should be noted that the memory of the systems and methods described herein is intended to include, but is not limited to, these and any other suitable types of memory.

电子设备300可以通过音频模块360、扬声器360A、受话器360B、音频采集模块(如下文涉及的麦克风)360C、以及应用处理器等实现音频功能。例如音乐播放，录音等。The electronic device 300 can implement audio functions through the audio module 360, the speaker 360A, the receiver 360B, the audio collection module (such as the microphone mentioned below) 360C, and the application processor. Such as music playback, recording, etc.

音频模块360用于将数字音频信息转换成模拟音频信号输出，也用于将模拟音频输入转换为数字音频信号。在一些实施例中，音频模块360可以设置于第一处理器311中，或将音频模块360的部分功能模块设置于第一处理器311中。扬声器360A，也称“喇叭”，用于将音频电信号转换为声音信号。受话器360B，也称“听筒”，用于将音频电信号转换成声音信号。麦克风，也称“话筒”，“传声器”，用于将声音信号转换为电信号。电子设备300可以设置至少一个麦克风(如4个麦克风)。The audio module 360 is used to convert digital audio information into analog audio signal output, and is also used to convert analog audio input into digital audio signals. In some embodiments, the audio module 360 may be disposed in the first processor 311 , or some functional modules of the audio module 360 may be disposed in the first processor 311 . Speaker 360A, also called "speaker", is used to convert audio electrical signals into sound signals. Receiver 360B, also called "earpiece", is used to convert audio electrical signals into sound signals. Microphone, also called "microphone" or "microphone", is used to convert sound signals into electrical signals. The electronic device 300 may be provided with at least one microphone (eg, 4 microphones).

按键380包括开关键、音量键等。按键380可以是机械按键。也可以是触摸式按键。电子设备300可以接收按键输入，产生与电子设备300的用户设置以及功能控制有关的键信号输入。指示器390可以是指示灯，可以用于指示电子设备的当前状态等。The buttons 380 include on/off keys, volume keys, etc. Key 380 may be a mechanical key. It can also be a touch button. The electronic device 300 may receive key input and generate key signal input related to user settings and function control of the electronic device 300 . The indicator 390 may be an indicator light, and may be used to indicate the current status of the electronic device, etc.

第一处理器311和第二处理器312通过执行存储器320中存储的程序、指令来执行本申请实施例提供的语音唤醒方法。第一处理器311和第二处理器312运行的程序可以基于操作系统，例如视窗(Windows)操作系统等。如图4所示，以第一处理器311和第二处理器312运行的程序基于/>为例，第一处理器311和第二处理器312运行的程序按照功能进行分层，可以包括应用程序层、系统服务层、算法库、硬件抽象层、内核层，以及驱动层。The first processor 311 and the second processor 312 execute the voice wake-up method provided by the embodiment of the present application by executing the programs and instructions stored in the memory 320 . The programs run by the first processor 311 and the second processor 312 may be based on an operating system, such as Windows operating system, etc. As shown in Figure 4, the program running on the first processor 311 and the second processor 312 is based on/> For example, the programs run by the first processor 311 and the second processor 312 are layered according to functions and may include an application layer, a system service layer, an algorithm library, a hardware abstraction layer, a kernel layer, and a driver layer.

驱动层用于驱动硬件抽象层的硬件资源。驱动层中可以包括音频采集模块驱动，音频采集模块驱动用于驱动音频采集模块，以通过音频采集模块采集音频数据。The driver layer is used to drive the hardware resources of the hardware abstraction layer. The driver layer may include an audio collection module driver, and the audio collection module driver is used to drive the audio collection module to collect audio data through the audio collection module.

内核层包括操作系统(operation system，OS)内核(kernel)。操作系统内核用于管理系统的进程、内存、驱动程序、文件系统和网络系统。The kernel layer includes the operating system (OS) kernel. The operating system kernel is used to manage the system's processes, memory, drivers, file systems, and network systems.

硬件抽象层用于将硬件抽象化。硬件抽象层可以包括拾音模块，拾音模块用于将音频采集模块硬件抽象化，将抽象化的音频采集模块供算法库中的语音唤醒算法调用，以向语音唤醒算法输出音频数据。The hardware abstraction layer abstracts the hardware. The hardware abstraction layer may include a sound pickup module. The sound pickup module is used to abstract the hardware of the audio collection module. The abstracted audio collection module is called by the voice wake-up algorithm in the algorithm library to output audio data to the voice wake-up algorithm.

算法库可以包括语音唤醒算法，语音唤醒算法用于执行本申请实施例提供的语音唤醒方法。语音唤醒算法可以是一种语音识别程序。具体的：The algorithm library may include a voice wake-up algorithm, and the voice wake-up algorithm is used to execute the voice wake-up method provided by the embodiments of this application. The voice wake-up algorithm can be a speech recognition program. specific:

第二处理器可以通过运行语音唤醒算法，检测音频数据中是否包括唤醒词。即第二处理器用于通过运行语音唤醒算法识别唤醒词。The second processor can detect whether the audio data includes a wake-up word by running a voice wake-up algorithm. That is, the second processor is used to identify the wake word by running a voice wake-up algorithm.

第一处理器可以通过运行语音唤醒算法，对音频数据进行语音识别，即检测对应的指令，从而执行对应的操作。例如，第一处理器检测到亮屏语音指令，控制电子设备从当前状态切换至亮屏状态；或者，第一处理器检测到业务切换语音指令，控制电子设备从播放当前节目切换至播放目标节目等。The first processor can perform voice recognition on the audio data by running a voice wake-up algorithm, that is, detect corresponding instructions, and thereby perform corresponding operations. For example, the first processor detects the voice command to turn on the screen and controls the electronic device to switch from the current state to the screen to light state; or the first processor detects the voice command to switch the service and controls the electronic device to switch from playing the current program to playing the target program. wait.

系统服务层可以包括语音唤醒服务，语音唤醒服务用于向语音唤醒应用提供调用语音唤醒算法的服务。The system service layer may include a voice wake-up service, which is used to provide voice wake-up applications with services for calling voice wake-up algorithms.

应用程序层可以包括语音唤醒应用，语音唤醒应用用于响应于音频数据中包括的语音唤醒指令执行对应的操作。The application layer may include a voice wake-up application configured to perform corresponding operations in response to voice wake-up instructions included in the audio data.

如图5所示，本申请实施例提供的电子设备中可以包括：电源端501和语音唤醒电路502。电源端501用于向语音唤醒电路502提供目标电压。语音唤醒电路502用于采集音频数据，并且用于对音频数据进行语音识别。As shown in FIG. 5 , the electronic device provided by the embodiment of the present application may include: a power terminal 501 and a voice wake-up circuit 502 . The power terminal 501 is used to provide a target voltage to the voice wake-up circuit 502 . The voice wake-up circuit 502 is used to collect audio data and perform voice recognition on the audio data.

其中，目标电压可以是由电子设备中的备用电源(standby power)提供的备用电压(standby voltage)(如5V)。通常，当电子设备连接外部的电源(即插上电源)时，备用电源便开始提供备用电压。The target voltage may be a standby voltage (such as 5V) provided by a standby power in the electronic device. Usually, when an electronic device is connected to an external power source (that is, plugged in), the backup power supply begins to provide backup voltage.

语音唤醒电路502可以包括：第一处理器311、第二处理器312、开关电路503、降压电路504，以及用于采集音频数据的音频采集模块360C。开关电路503的第一端耦合至第一处理器311，开关电路503的第二端用于耦合至电源端501，开关电路503的第三端耦合至降压电路504的第一端。降压电路504的第二端耦合至音频采集模块360C。第一处理器311的功耗大于第二处理器312的功耗。The voice wake-up circuit 502 may include: a first processor 311, a second processor 312, a switch circuit 503, a buck circuit 504, and an audio collection module 360C for collecting audio data. The first terminal of the switch circuit 503 is coupled to the first processor 311 , the second terminal of the switch circuit 503 is coupled to the power terminal 501 , and the third terminal of the switch circuit 503 is coupled to the first terminal of the buck circuit 504 . The second terminal of the buck circuit 504 is coupled to the audio acquisition module 360C. The power consumption of the first processor 311 is greater than the power consumption of the second processor 312 .

当电子设备处于待机状态时，第一处理器311用于控制开关电路503导通，以使电源端501通过开关电路503向降压电路504提供目标电压，降压电路504用于对目标电压降压后向音频采集模块360C供电。这样，当电子设备处于待机状态时，音频采集模块仍然能够采集音频数据。第一处理器311还用于指示第二处理器312检测音频数据中是否包括唤醒词之后进入休眠状态。这样，可以进一步降低电子设备在待机状态时的功耗，而且保证了电子设备在待机状态时，仍然能够检测唤醒词(即进行语音侦测)。第二处理器312通过运行语音唤醒算法检测唤醒词，如果检测到唤醒词，如图6所示，第二处理器唤醒第一处理器。第一处理器还用于运行语音唤醒算法对音频数据进行语音识别，从而执行对应的操作。由此可见，本申请实施例提供的电子设备在处于待机状态时，第一处理器不用运行语音唤醒算法进行语音侦测，通过功耗较低的第二处理器持续地运行语音唤醒算法进行语音侦测即可，同时，也不需要持续地运行语音唤醒算法进行语音识别。这样，降低了第一处理器的功耗，从而使电子设备在处于待机状态时能够低功耗的实现语音唤醒功能。When the electronic device is in a standby state, the first processor 311 is used to control the switch circuit 503 to turn on, so that the power terminal 501 provides the target voltage to the voltage reduction circuit 504 through the switch circuit 503, and the voltage reduction circuit 504 is used to reduce the target voltage. After pressing, power is supplied to the audio collection module 360C. In this way, when the electronic device is in standby state, the audio collection module can still collect audio data. The first processor 311 is also used to instruct the second processor 312 to detect whether the audio data includes a wake-up word and then enter the sleep state. In this way, the power consumption of the electronic device in the standby state can be further reduced, and it is ensured that the electronic device can still detect the wake-up word (ie, perform voice detection) in the standby state. The second processor 312 detects the wake-up word by running the voice wake-up algorithm. If the wake-up word is detected, as shown in Figure 6, the second processor wakes up the first processor. The first processor is also used to run a voice wake-up algorithm to perform voice recognition on the audio data, thereby performing corresponding operations. It can be seen that when the electronic device provided by the embodiment of the present application is in a standby state, the first processor does not need to run the voice wake-up algorithm for voice detection, and the second processor with lower power consumption continuously runs the voice wake-up algorithm for voice detection. Detection is enough. At the same time, there is no need to continuously run the voice wake-up algorithm for speech recognition. In this way, the power consumption of the first processor is reduced, thereby enabling the electronic device to implement the voice wake-up function with low power consumption when it is in a standby state.

可选的，为了进一步确保电子设备在处于待机状态时能够低功耗的实现语音唤醒功能，第一处理器311指示第二处理器312检测音频数据中是否包括唤醒词的过程，具体可以包括：首先，第一处理器311获取电子设备的当前功耗；然后，第一处理器311将当前功耗与目标功耗进行比较，如果当前功耗小于目标功耗，则第一处理器311指示第二处理器312检测音频数据中是否包括唤醒词。其中，目标功耗可以小于上述预设功耗。例如，如果预设功耗为0.5W，则目标功耗可以为0.48W。Optionally, in order to further ensure that the electronic device can realize the voice wake-up function with low power consumption when it is in the standby state, the first processor 311 instructs the second processor 312 to detect whether the audio data includes the wake-up word, which may specifically include: First, the first processor 311 obtains the current power consumption of the electronic device; then, the first processor 311 compares the current power consumption with the target power consumption. If the current power consumption is less than the target power consumption, the first processor 311 indicates the first power consumption of the electronic device. The second processor 312 detects whether the audio data includes the wake word. The target power consumption may be less than the above-mentioned preset power consumption. For example, if the preset power consumption is 0.5W, the target power consumption can be 0.48W.

通常，当电子设备处于待机状态时，电子设备中的大部分模块都会下电，从而保证电子设备的功耗小于预设功耗。此时，如果本该下电的模块由于故障等原因没有正常下电，那么电子设备的当前功耗会超过预设功耗。而且，电子设备处于待机状态时，本该下电的音频采集模块上电了，这会导致电子设备的当前功耗增大。因此，为了确保电子设备在处于待机状态时能够低功耗的实现语音唤醒功能，第一处理器还需要判断音频采集模块上电后，电子设备的当前功耗是否超过比预设功耗更小的目标功耗。如果当前功耗小于目标功耗，则第一处理器指示第二处理器检测音频数据中是否包括唤醒词。如果当前功耗大于目标功耗，则表示本该下电的某些模块没有下电，此时，第一处理器不会指示第二处理器检测音频数据中是否包括唤醒词，同时第一处理器也不会检测音频数据中是否包括唤醒词。也就是说，如果当前功耗大于目标功耗，第一处理器会禁用语音唤醒功能，并且控制本该下电而没有下电的某些模块下电，直至第一处理器确定电子设备的当前功耗小于目标功耗，才会启用语音唤醒功能，即指示第二处理器检测唤醒词。Usually, when the electronic device is in a standby state, most modules in the electronic device will be powered off to ensure that the power consumption of the electronic device is less than the preset power consumption. At this time, if the module that should be powered off is not powered off normally due to a fault or other reasons, the current power consumption of the electronic device will exceed the preset power consumption. Moreover, when the electronic device is in standby mode, the audio collection module that should be powered off is powered on, which will cause the current power consumption of the electronic device to increase. Therefore, in order to ensure that the electronic device can implement the voice wake-up function with low power consumption when it is in the standby state, the first processor also needs to determine whether the current power consumption of the electronic device exceeds the preset power consumption after the audio collection module is powered on. target power consumption. If the current power consumption is less than the target power consumption, the first processor instructs the second processor to detect whether the audio data includes the wake word. If the current power consumption is greater than the target power consumption, it means that some modules that should have been powered off have not been powered off. At this time, the first processor will not instruct the second processor to detect whether the audio data includes the wake word. At the same time, the first processor The device also does not detect whether the audio data includes a wake word. That is to say, if the current power consumption is greater than the target power consumption, the first processor will disable the voice wake-up function and control some modules that should be powered off but are not powered off until the first processor determines the current power consumption of the electronic device. Only when the power consumption is less than the target power consumption will the voice wake-up function be enabled, which instructs the second processor to detect the wake-up word.

示例性的，第一处理器可以从电子设备的电源管理模块处获取电子设备的当前功耗，具体过程本申请实施例不作具体描述和限定。For example, the first processor may obtain the current power consumption of the electronic device from the power management module of the electronic device. The specific process is not specifically described or limited in the embodiments of this application.

可选的，如图6所示，当本申请实施例提供的电子设备处于熄屏状态，并且无音频音箱业务时，第一处理器还用于控制电子设备从熄屏状态切换至待机状态。Optionally, as shown in Figure 6, when the electronic device provided by the embodiment of the present application is in the screen-off state and there is no audio speaker service, the first processor is also used to control the electronic device to switch from the screen-off state to the standby state.

电子设备处于熄屏状态，并且电子设备无音频音箱业务，相当于，电子设备既没有播放视频节目，也没有播放音频节目。此时，第一处理器控制电子设备从熄屏状态切换到待机状态，使电子设备中的大部分模块下电，可以极大地降低电子设备的功耗，并且使电子设备仍然具有语音唤醒功能。The electronic device is in the screen-off state, and the electronic device does not have audio speaker services. This is equivalent to the electronic device playing neither video programs nor audio programs. At this time, the first processor controls the electronic device to switch from the screen-off state to the standby state, powering off most of the modules in the electronic device, which can greatly reduce the power consumption of the electronic device and enable the electronic device to still have the voice wake-up function.

在一种实施例中，当电子设备在预设时间段内均无音频音箱业务时，第一处理器才会确定电子设备无音频音箱业务。这样，可以确保电子设备确实无音频音箱业务，避免电子设备中部分模块频繁地上电、下电，从而可以降低电子设备中这部分模块的故障率，并且延长这部分模块的使用寿命。In one embodiment, when the electronic device has no audio speaker service within a preset time period, the first processor determines that the electronic device has no audio speaker service. In this way, it can be ensured that the electronic equipment does not have audio speaker services and avoid frequent power-on and power-off of some modules in the electronic equipment, thereby reducing the failure rate of these modules in the electronic equipment and extending the service life of these modules.

可选的，结合图6，如图7所示，当本申请实施例提供的电子设备处于亮屏状态时，第一处理器指示第二处理器检测唤醒词。也就是说，在电子设备处于亮屏状态时，检测唤醒词(即语音侦测)是由低功耗的第二处理器来完成的。当第二处理器检测到唤醒词后，第二处理器唤醒第一处理器，第一处理器再对音频数据进行语音识别。这样，降低了第一处理器的功耗，从而使电子设备在处于亮屏状态时能够低功耗的实现语音唤醒功能。Optionally, with reference to Figure 6, as shown in Figure 7, when the electronic device provided by the embodiment of the present application is in a bright screen state, the first processor instructs the second processor to detect the wake-up word. That is to say, when the electronic device is in the screen-on state, detecting the wake-up word (ie, voice detection) is completed by the low-power second processor. When the second processor detects the wake-up word, the second processor wakes up the first processor, and the first processor then performs speech recognition on the audio data. In this way, the power consumption of the first processor is reduced, thereby enabling the electronic device to implement the voice wake-up function with low power consumption when the screen is on.

下面结合图5，以及图8和图9，简单描述本申请实施例提供的电子设备的电路结构。The circuit structure of the electronic device provided by the embodiment of the present application will be briefly described below with reference to FIG. 5, as well as FIGS. 8 and 9.

结合图5，如图8所示，开关电路503可以包括：第一开关子电路5031和第二开关子电路5032。其中，第一开关子电路5031的第一端耦合至第一处理器311，第一开关子电路5031的第二端用于耦合至电源端501，第一开关子电路5031的第三端耦合至第二开关子电路5032的第一端。第二开关子电路5032的第二端耦合至电源端501，第二开关子电路5032的第三端耦合至降压电路504。In conjunction with FIG. 5 , as shown in FIG. 8 , the switch circuit 503 may include: a first switch sub-circuit 5031 and a second switch sub-circuit 5032 . Wherein, the first terminal of the first switch sub-circuit 5031 is coupled to the first processor 311, the second terminal of the first switch sub-circuit 5031 is used to couple to the power terminal 501, and the third terminal of the first switch sub-circuit 5031 is coupled to The first terminal of the second switch sub-circuit 5032. The second terminal of the second switch sub-circuit 5032 is coupled to the power terminal 501 , and the third terminal of the second switch sub-circuit 5032 is coupled to the buck circuit 504 .

当电子设备处于待机状态时，第一处理器311用于控制第一开关子电路5031导通，以使第二开关子电路5032导通。这样，电源端501可以通过第二开关子电路5032向降压电路504提供目标电压。降压电路504便可以对目标电压进行降压后向音频采集模块360C供电，从而在电子设备处于待机状态时，音频采集模块360C能够采集音频数据。When the electronic device is in a standby state, the first processor 311 is used to control the first switch sub-circuit 5031 to turn on, so that the second switch sub-circuit 5032 turns on. In this way, the power terminal 501 can provide the target voltage to the buck circuit 504 through the second switch sub-circuit 5032. The voltage reduction circuit 504 can reduce the target voltage and then supply power to the audio collection module 360C, so that when the electronic device is in a standby state, the audio collection module 360C can collect audio data.

可选的，如图8所示，上述第一开关子电路5031可以包括：第一电阻R1、第二电阻R2、NPN型三极管Q1和第三电阻R3。第一电阻R1的第一端为第一开关子电路5031的第一端，第一电阻R1的第二端为第一开关子电路5031的第二端。第二电阻R2的第一端耦合至第一电阻R1的第一端，第二电阻R2的第二端耦合至NPN型三极管Q1的基极(b)。NPN型三极管Q1的发射极(e)用于耦合至接地端，NPN型三极管Q1的集电极(c)耦合至第三电阻R3的第一端。第三电阻R3的第二端为第一开关子电路5031的第三端。当电子设备处于待机状态时，第一处理器311具体用于控制NPN型三极管Q1导通，从而使得第一开关子电路5031导通。Optionally, as shown in FIG. 8 , the above-mentioned first switch sub-circuit 5031 may include: a first resistor R1, a second resistor R2, an NPN transistor Q1 and a third resistor R3. The first terminal of the first resistor R1 is the first terminal of the first switch sub-circuit 5031 , and the second terminal of the first resistor R1 is the second terminal of the first switch sub-circuit 5031 . The first terminal of the second resistor R2 is coupled to the first terminal of the first resistor R1, and the second terminal of the second resistor R2 is coupled to the base (b) of the NPN transistor Q1. The emitter (e) of the NPN transistor Q1 is coupled to the ground terminal, and the collector (c) of the NPN transistor Q1 is coupled to the first terminal of the third resistor R3. The second terminal of the third resistor R3 is the third terminal of the first switch sub-circuit 5031. When the electronic device is in a standby state, the first processor 311 is specifically configured to control the NPN transistor Q1 to turn on, thereby turning on the first switch sub-circuit 5031.

可选的，如图8所示，上述第二开关子电路5032可以包括：第四电阻R4和P型场效应管Q2。第四电阻R4的第一端为第二开关子电路5032的第一端，第四电阻R4的第二端为第二开关子电路5032的第二端。P型场效应管Q2的栅极(g)耦合至第四电阻R4的第一端，P型场效应管Q2的源极(s)耦合至第四电阻R4的第二端，P型场效应管Q2的漏极(d)耦合至降压电路504。Optionally, as shown in FIG. 8 , the above-mentioned second switch sub-circuit 5032 may include: a fourth resistor R4 and a P-type field effect transistor Q2. The first terminal of the fourth resistor R4 is the first terminal of the second switch sub-circuit 5032 , and the second terminal of the fourth resistor R4 is the second terminal of the second switch sub-circuit 5032 . The gate (g) of the P-type field effect transistor Q2 is coupled to the first terminal of the fourth resistor R4, and the source (s) of the P-type field effect transistor Q2 is coupled to the second terminal of the fourth resistor R4. The drain (d) of tube Q2 is coupled to buck circuit 504.

其中，第一电阻R1为上拉电阻，用于增大NPN型三极管Q1的基极的驱动电流，以使当第一处理器311的GPIO接口输出高电平的电压时，确保NPN型三极管Q1导通。第二电阻R2为基极限流电阻，其第一端耦合至第一处理器311的GPIO接口，其第二端耦合至NPN型三极管Q1的基极(b)。基于此，可以防止NPN型三极管Q1的基极(b)的电流过大而导致NPN型三极管Q1被烧坏。Among them, the first resistor R1 is a pull-up resistor, which is used to increase the driving current of the base of the NPN transistor Q1, so that when the GPIO interface of the first processor 311 outputs a high-level voltage, the NPN transistor Q1 is ensured. conduction. The second resistor R2 is a base current-limiting resistor, its first end is coupled to the GPIO interface of the first processor 311, and its second end is coupled to the base (b) of the NPN transistor Q1. Based on this, it can be prevented that the current in the base (b) of the NPN transistor Q1 is too large and causes the NPN transistor Q1 to be burned out.

需要说明的是，本申请实施例涉及的第一处理器311内置有下拉电阻，该下拉电阻的第一端耦合至第一电阻R1的第一端，该下拉电阻的第二端用于耦合至接地端。通过该下拉电阻，可以在第一处理器311的GPIO接口的输出信号不确定(即NPN三极管Q1的基极的输入信号)不确定时，使NPN三极管Q1的基极能够有效接地，从而使得NPN三极管Q1处于关断状态。It should be noted that the first processor 311 involved in the embodiment of the present application has a built-in pull-down resistor, the first end of the pull-down resistor is coupled to the first end of the first resistor R1, and the second end of the pull-down resistor is used to couple to Ground terminal. Through this pull-down resistor, when the output signal of the GPIO interface of the first processor 311 is uncertain (that is, the input signal of the base of the NPN transistor Q1) is uncertain, the base of the NPN transistor Q1 can be effectively grounded, thereby making the NPN Transistor Q1 is in the off state.

NPN型三极管是电流控制型器件，当第一处理器311通过GPIO接口向NPN型三极管Q1的基极(b)提供的高电平的电压大于导通电压时，NPN型三极管Q1即可导通，当第一处理器311通过GPIO接口向NPN型三极管Q1的基极(b)提供低电平的电压时，NPN型三极管Q1关断。本申请实施例中，在电子设备处于待机状态时，为了使音频采集模块360C能够采集音频数据，第一处理器311通过GPIO接口向NPN型三极管Q1的基极提供高电平的电压。The NPN transistor is a current-controlled device. When the high-level voltage provided by the first processor 311 to the base (b) of the NPN transistor Q1 through the GPIO interface is greater than the turn-on voltage, the NPN transistor Q1 can be turned on. , when the first processor 311 provides a low-level voltage to the base (b) of the NPN transistor Q1 through the GPIO interface, the NPN transistor Q1 is turned off. In the embodiment of the present application, when the electronic device is in a standby state, in order to enable the audio collection module 360C to collect audio data, the first processor 311 provides a high-level voltage to the base of the NPN transistor Q1 through the GPIO interface.

当NPN型三极管Q1导通后，第三电阻R3和第四电阻R4对电源端501提供的目标电压进行分压后，使得P型场效应管Q2的栅极(g)的电压低于P型场效应管Q2的源极(s)的电压，并且，使得P型场效应管Q2的栅源电压(V_gs)满足P型场效应管Q2的导通条件，从而使得P型场效应管Q2导通。P型场效应管Q2导通后，电源端501通过P型场效应管Q2的源极(s)、P型场效应管Q2的漏极(d)向降压电路504提供目标电压。When the NPN transistor Q1 is turned on, the third resistor R3 and the fourth resistor R4 divide the target voltage provided by the power supply terminal 501, so that the voltage of the gate (g) of the P-type field effect transistor Q2 is lower than that of the P-type transistor Q1. The voltage of the source (s) of the field effect transistor Q2, and makes the gate-source voltage (V_gs ) of the P-type field effect transistor Q2 meet the conduction conditions of the P-type field effect transistor Q2, so that the P-type field effect transistor Q2 conduction. After the P-type FET Q2 is turned on, the power terminal 501 provides the target voltage to the buck circuit 504 through the source (s) of the P-type FET Q2 and the drain (d) of the P-type FET Q2.

需要说明的是，三极管为电流控制型器件，其导通电压较小(如0.7V或0.6V)。通常，处理器的GPIO接口输出的电压大于该导通电压。因此，处理器可以直接驱动三极管。而场效应管为电压控制型器件，处理器的GPIO接口输出的电压无法驱动功率较大的场效应管。因此，本申请实施例中，第一处理器通过驱动NPN型三极管Q1后，再通过第三电阻R3和第四电阻R4对电源端的电压进行分压后，使P型场效应管Q2的源极(s)的电压、栅极(g)的电压满足导通条件，以此来驱动P型场效应管Q2。It should be noted that the transistor is a current-controlled device, and its conduction voltage is small (such as 0.7V or 0.6V). Usually, the voltage output by the processor's GPIO interface is greater than the turn-on voltage. Therefore, the processor can directly drive the transistor. The field effect transistor is a voltage-controlled device, and the voltage output by the processor's GPIO interface cannot drive the larger power field effect transistor. Therefore, in the embodiment of the present application, after the first processor drives the NPN transistor Q1, and then divides the voltage at the power supply terminal through the third resistor R3 and the fourth resistor R4, the source of the P-type field effect transistor Q2 is The voltage of (s) and the voltage of gate (g) meet the conduction conditions to drive the P-type field effect transistor Q2.

可选的，如图8所示，上述第一开关子电路5031还可以包括第一电容C1。第一电容C1的第一端耦合至NPN型三极管Q1的基极(b)，第一电容C1的第二端耦合至NPN型三极管Q1的发射极(e)。第一电容C1为旁路电容，可以用于高频滤波，从而提升NPN型三极管Q1的抗干扰能力。Optionally, as shown in FIG. 8 , the above-mentioned first switch sub-circuit 5031 may also include a first capacitor C1. The first terminal of the first capacitor C1 is coupled to the base (b) of the NPN transistor Q1, and the second terminal of the first capacitor C1 is coupled to the emitter (e) of the NPN transistor Q1. The first capacitor C1 is a bypass capacitor and can be used for high-frequency filtering, thereby improving the anti-interference ability of the NPN transistor Q1.

可选的，如图8所示，上述第二开关子电路5032还可以包括：第五电阻R5、第二电容C2和第三电容C3。第五电阻R5的第一端耦合至第四电阻R4的第一端，第五电阻R5的第二端耦合至P型场效应管Q2的栅极(g)。第二电容C2的第一端耦合至P型场效应管Q2的源极(s)，第二电容C2的第二端耦合至P型场效应管Q2的栅极(g)。第三电容C3的第一端耦合至P型场效应管Q2的漏极(d)，第三电容C3的第二端用于耦合至接地端。Optionally, as shown in FIG. 8 , the above-mentioned second switch sub-circuit 5032 may also include: a fifth resistor R5, a second capacitor C2, and a third capacitor C3. The first terminal of the fifth resistor R5 is coupled to the first terminal of the fourth resistor R4, and the second terminal of the fifth resistor R5 is coupled to the gate (g) of the P-type field effect transistor Q2. The first terminal of the second capacitor C2 is coupled to the source (s) of the P-type field effect transistor Q2, and the second terminal of the second capacitor C2 is coupled to the gate (g) of the P-type field effect transistor Q2. The first terminal of the third capacitor C3 is coupled to the drain (d) of the P-type field effect transistor Q2, and the second terminal of the third capacitor C3 is coupled to the ground terminal.

其中，第五电阻R5用于保护P型场效应管Q2的源极(s)和漏极(d)不被击穿。第二电容C2用于控制P型场效应管Q2的导通-关断时间。第三电容C3用于对降压电路504的输出电压进行滤波。Among them, the fifth resistor R5 is used to protect the source (s) and drain (d) of the P-type field effect transistor Q2 from breakdown. The second capacitor C2 is used to control the on-off time of the P-type field effect transistor Q2. The third capacitor C3 is used to filter the output voltage of the buck circuit 504 .

可选的，如图8所示，上述第二开关子电路5032还可以包括：第四电容C4、第五电容C5和第六电容C6。第四电容C4的第一端、第五电容C5的第一端用于耦合至电源端501，第四电容C4的第二端、第五电容C5的第二端用于耦合至接地端，用于进行滤波。第六电容C6与第三电容C3并联，用于加强滤波。Optionally, as shown in FIG. 8 , the above-mentioned second switch sub-circuit 5032 may also include: a fourth capacitor C4, a fifth capacitor C5, and a sixth capacitor C6. The first terminal of the fourth capacitor C4 and the first terminal of the fifth capacitor C5 are used for coupling to the power terminal 501, and the second terminal of the fourth capacitor C4 and the second terminal of the fifth capacitor C5 are used for coupling to the ground terminal. for filtering. The sixth capacitor C6 is connected in parallel with the third capacitor C3 for enhancing filtering.

可选的，结合图5，如图9和图10所示，上述开关电路503可以包括第三开关子电路。第三开关子电路的第一端耦合至第一处理器311，第三开关子电路的第二端耦合至电源端501，第三开关子电路的第三端耦合至降压电路504的第一端。当电子设备处于待机状态时，第一处理器311具体用于控制第三开关子电路导通，从而电源端501向降压电路504提供目标电压。Optionally, in conjunction with Figure 5, as shown in Figures 9 and 10, the above-mentioned switch circuit 503 may include a third switch sub-circuit. The first terminal of the third switching sub-circuit is coupled to the first processor 311 , the second terminal of the third switching sub-circuit is coupled to the power terminal 501 , and the third terminal of the third switching sub-circuit is coupled to the first terminal of the buck circuit 504 . end. When the electronic device is in the standby state, the first processor 311 is specifically configured to control the third switch sub-circuit to be turned on, so that the power terminal 501 provides the target voltage to the buck circuit 504 .

在一种实施例中，结合图5，如图9所示，上述第三开关子电路可以包括：第十电阻R10、第十一电阻R11和NPN型三极管Q3。第十电阻R10的第一端为第三开关子电路的第一端，第十电阻R10的第二端为第三开关子电路的第二端。第十一电阻R11的第一端耦合至第十电阻R10的第一端，第十一电阻R11的第二端耦合至NPN型三极管Q3的基极(b)。NPN型三极管Q3的发射极(e)用于耦合至接地端，NPN型三极管Q3的集电极(c)为第三开关子电路的第三端。降压电路504的第三端耦合至电源端501。第一处理器311具体用于：当电子设备处于待机状态时，控制NPN型三极管Q3导通。In one embodiment, as shown in FIG. 9 in conjunction with FIG. 5 , the above-mentioned third switch sub-circuit may include: a tenth resistor R10 , an eleventh resistor R11 and an NPN transistor Q3 . The first terminal of the tenth resistor R10 is the first terminal of the third switch sub-circuit, and the second terminal of the tenth resistor R10 is the second terminal of the third switch sub-circuit. The first terminal of the eleventh resistor R11 is coupled to the first terminal of the tenth resistor R10, and the second terminal of the eleventh resistor R11 is coupled to the base (b) of the NPN transistor Q3. The emitter (e) of the NPN transistor Q3 is used to couple to the ground terminal, and the collector (c) of the NPN transistor Q3 is the third terminal of the third switch sub-circuit. The third terminal of the buck circuit 504 is coupled to the power terminal 501 . The first processor 311 is specifically used to control the NPN transistor Q3 to turn on when the electronic device is in a standby state.

如图9所示，第三开关子电路还可以包括第十一电容C11。第十一电容C11的第一端耦合至NPN型三极管Q2的基极(b)，第十一电容C11的第二端耦合至接地端。第十一电容C11为旁路电容，可以用于高频滤波，从而提升NPN型三极管Q3的抗干扰能力。As shown in Figure 9, the third switch sub-circuit may also include an eleventh capacitor C11. The first terminal of the eleventh capacitor C11 is coupled to the base (b) of the NPN transistor Q2, and the second terminal of the eleventh capacitor C11 is coupled to the ground terminal. The eleventh capacitor C11 is a bypass capacitor and can be used for high-frequency filtering, thereby improving the anti-interference ability of the NPN transistor Q3.

在另一种实施例中，结合图5，如图10所示，上述第三开关子电路可以包括P型场效应管Q4。P型场效应管Q4的栅极(g)耦合至第一处理器，P型场效应管Q4的源极(s)耦合至电源端501，P型场效应管Q4的漏极(d)耦合至降压电路504的第一端。In another embodiment, as shown in FIG. 10 in conjunction with FIG. 5 , the above-mentioned third switch sub-circuit may include a P-type field effect transistor Q4. The gate (g) of the P-type field effect transistor Q4 is coupled to the first processor, the source (s) of the P-type field effect transistor Q4 is coupled to the power terminal 501, and the drain (d) of the P-type field effect transistor Q4 is coupled to the first terminal of the buck circuit 504.

当电子设备处于待机状态时，第一处理器311的GPIO接口可以输出低电平的电压。此时，P型场效应管Q4的栅极(g)的电压，以及源极(s)的电压满足导通条件，以此来驱动P型场效应管Q4，使得P型场效应管Q4导通，电源端通过P型场效应管Q4的源极(s)、漏极(d)向降压电路504供电。When the electronic device is in a standby state, the GPIO interface of the first processor 311 can output a low-level voltage. At this time, the voltage of the gate (g) and the source (s) of the P-type field effect transistor Q4 meet the conduction conditions, thereby driving the P-type field effect transistor Q4, causing the P-type field effect transistor Q4 to conduct. The power supply terminal supplies power to the buck circuit 504 through the source (s) and drain (d) of the P-type field effect transistor Q4.

如图10所示，第三开关子电路还可以包括：第十二电阻R12、第十二电容C12、第十三电容C13和第十四电容C14。第十二电阻R12的第一端耦合至第第一处理器311，第十二电阻R12的第二端耦合至P型场效应管Q4的栅极(g)。第十二电容C12的第一端耦合至P型场效应管Q4的源极(s)，第十二电容C12的第二端耦合至P型场效应管Q4的栅极(g)。第十三电容C13的第一端和第十四电容C14的第一端耦合至P型场效应管Q4的漏极(d)，第十三电容C13的第一端和第十四电容C14的第二端耦合至接地端。As shown in Figure 10, the third switch sub-circuit may also include: a twelfth resistor R12, a twelfth capacitor C12, a thirteenth capacitor C13 and a fourteenth capacitor C14. The first terminal of the twelfth resistor R12 is coupled to the first processor 311, and the second terminal of the twelfth resistor R12 is coupled to the gate (g) of the P-type field effect transistor Q4. The first end of the twelfth capacitor C12 is coupled to the source (s) of the P-type field effect transistor Q4, and the second end of the twelfth capacitor C12 is coupled to the gate (g) of the P-type field effect transistor Q4. The first terminal of the thirteenth capacitor C13 and the first terminal of the fourteenth capacitor C14 are coupled to the drain (d) of the P-type field effect transistor Q4, and the first terminal of the thirteenth capacitor C13 and the fourteenth capacitor C14 are The second terminal is coupled to ground.

需要说明的是，开关电路的具体结构与音频采集模块的功率有关。开关电路的具体结构可以输出的电平也不同。It should be noted that the specific structure of the switch circuit is related to the power of the audio collection module. The specific structure of the switching circuit can also output different levels.

进一步的，结合图5，如图11所示，上述降压电路504可以包括：降压器件5041、第六电阻R6和第七电阻R7。降压器件5041的输入端(IN)耦合至开关电路503的第三端；降压器件5041的输出端(OUT)耦合至第六电阻R6的第一端、降压器件5041的接地端，以及音频采集模块360C；降压器件5041的调整端(ADJ)耦合至第六电阻R6的第二端、第七电阻R7的第一端；第七电阻R7的第二端用于耦合至接地端。Further, with reference to FIG. 5 , as shown in FIG. 11 , the above-described voltage-reducing circuit 504 may include: a voltage-reducing device 5041 , a sixth resistor R6 and a seventh resistor R7 . The input terminal (IN) of the buck device 5041 is coupled to the third terminal of the switch circuit 503; the output terminal (OUT) of the buck device 5041 is coupled to the first terminal of the sixth resistor R6, the ground terminal of the buck device 5041, and Audio acquisition module 360C; the adjustment terminal (ADJ) of the buck device 5041 is coupled to the second terminal of the sixth resistor R6 and the first terminal of the seventh resistor R7; the second terminal of the seventh resistor R7 is used for coupling to the ground terminal.

示例性的，降压器件5041可以是型号为AS1117L-ADJ的低压降正向稳压器，但不仅限于此。当降压器件5041为该低压降正向稳压器时，本申请实施例提供的降压电路504的输出电压V_out可以通过以下公式(1)表示：By way of example, the buck device 5041 may be a low-voltage drop forward regulator modeled as AS1117L-ADJ, but is not limited to this. When the buck device 5041 is a low-dropout forward regulator, the output voltage V_out of the buck circuit 504 provided by the embodiment of the present application can be expressed by the following formula (1):

其中，V_ref为降压器件5041的基准电压，R₆为第六电阻R6的阻值，R₇为第七电阻R7的阻值。Among them, V_ref is the reference voltage of the buck device 5041, R₆ is the resistance of the sixth resistor R6, and R₇ is the resistance of the seventh resistor R7.

由公式(1)可知，降压电路504的输出电压V_out与降压器件5041的基准电压V_ref、第六电阻R6的阻值，以及第七电阻R7的阻值有关。因此，当降压器件5041确定之后，可以通过选择合适的第六电阻R6和第七电阻R7来调整降压电路504的输出电压V_out，从而满足音频采集模块360C的需求电压。It can be seen from formula (1) that the output voltage V_out of the buck circuit 504 is related to the reference voltage V_ref of the buck device 5041, the resistance of the sixth resistor R6, and the resistance of the seventh resistor R7. Therefore, after the buck device 5041 is determined, the output voltage V_out of the buck circuit 504 can be adjusted by selecting appropriate sixth resistor R6 and seventh resistor R7 to meet the required voltage of the audio collection module 360C.

可选的，如图11所示，上述降压电路504还可以包括：第八电阻R8、第七电容C7、第八电容C8，以及第九电容C9。第八电阻R8的第一端耦合至开关电路503的第三端，第八电阻R8的第二端耦合至降压器件5041的输入端(IN)。第七电容C7的第一端耦合至降压器件5041的输入端(IN)，第七电容C7的第二端用于耦合至接地端。第八电容C8的第一端，以及第九电容C9的第一端耦合至降压器件5041的输出端(OUT)，第八电容C8的第二端，以及第九电容C9的第二端用于耦合至接地端。Optionally, as shown in FIG. 11 , the above-mentioned voltage reducing circuit 504 may also include: an eighth resistor R8, a seventh capacitor C7, an eighth capacitor C8, and a ninth capacitor C9. The first terminal of the eighth resistor R8 is coupled to the third terminal of the switch circuit 503 , and the second terminal of the eighth resistor R8 is coupled to the input terminal (IN) of the buck device 5041 . The first terminal of the seventh capacitor C7 is coupled to the input terminal (IN) of the buck device 5041, and the second terminal of the seventh capacitor C7 is used for coupling to the ground terminal. The first terminal of the eighth capacitor C8 and the first terminal of the ninth capacitor C9 are coupled to the output terminal (OUT) of the buck device 5041. The second terminal of the eighth capacitor C8 and the second terminal of the ninth capacitor C9 are coupled to the output terminal (OUT) of the buck device 5041. to be coupled to ground.

其中，第八电阻R8用于限流，以保护降压电路504。第七电容C7、第八电容C8，以及第九电容C9用于滤波。Among them, the eighth resistor R8 is used for current limiting to protect the buck circuit 504 . The seventh capacitor C7, the eighth capacitor C8, and the ninth capacitor C9 are used for filtering.

可选的，如图11所示，上述降压电路504还可以包括：第十电容C10和第九电阻R9。第十电容C10与第六电阻R6并联，用于加强滤波。第九电阻R9串联在降压器件5041的输出端(OUT)与音频采集模块360C之间，用于限流。Optionally, as shown in Figure 11, the above-mentioned voltage reducing circuit 504 may also include: a tenth capacitor C10 and a ninth resistor R9. The tenth capacitor C10 is connected in parallel with the sixth resistor R6 for enhancing filtering. The ninth resistor R9 is connected in series between the output terminal (OUT) of the voltage-reducing device 5041 and the audio acquisition module 360C for current limiting.

以下实施例中所述的方法，可以应用于具有上述软硬件结构的电子设备(如智能语音电视机等)。The methods described in the following embodiments can be applied to electronic devices (such as smart voice televisions, etc.) with the above-mentioned software and hardware structures.

如图12所示，本申请实施例提供的语音唤醒方法可以包括：As shown in Figure 12, the voice wake-up method provided by the embodiment of the present application may include:

S1201、第一处理器获取电子设备的当前状态。S1201. The first processor obtains the current status of the electronic device.

电子设备的当前状态可以包括：熄屏状态、亮屏状态和待机状态等。第一处理器可以通过获取电子设备的显示屏的状态信息、电子设备的功耗信息，以及电子设备的指示灯(如发光二极管(light emitting diode，LED))的状态信息等中的至少一种信息来获取电子设备的当前状态。The current status of the electronic device may include: screen off status, screen on status, standby status, etc. The first processor may obtain at least one of status information of the display screen of the electronic device, power consumption information of the electronic device, and status information of the indicator light (such as a light emitting diode (LED)) of the electronic device. information to obtain the current status of the electronic device.

在一种实施例中，当电子设备的显示屏处于工作状态时，第一处理器可以确定电子设备的当前状态为亮屏状态。当电子设备的显示屏未处于工作状态时，电子设备可能处于熄屏状态，也可能处于待机状态。此时，第一处理器还需结合电子设备的当前功耗来确定电子设备处于熄屏状态还是待机状态。如果电子设备的当前功耗小于预设功耗，则第一处理器可以确定电子设备处于待机状态，否则，第一处理器确定电子设备处于熄屏状态。In one embodiment, when the display screen of the electronic device is in a working state, the first processor may determine that the current state of the electronic device is the screen-on state. When the display screen of the electronic device is not in working condition, the electronic device may be in a screen-off state or in a standby state. At this time, the first processor also needs to determine whether the electronic device is in a screen-off state or a standby state based on the current power consumption of the electronic device. If the current power consumption of the electronic device is less than the preset power consumption, the first processor may determine that the electronic device is in the standby state; otherwise, the first processor determines that the electronic device is in the screen-off state.

在另一种实施例中，当电子设备的显示屏处于工作状态时，第一处理器可以确定电子设备的当前状态为亮屏状态。当电子设备的显示屏未处于工作状态时，如果电子设备的指示灯处于常亮状态，则第一处理器可以确定电子设备处于待机状态，如果电子设备的指示灯处于闪烁状态，则第一处理器可以确定电子设备处于熄屏状态。In another embodiment, when the display screen of the electronic device is in a working state, the first processor may determine that the current state of the electronic device is the screen-on state. When the display screen of the electronic device is not in the working state, if the indicator light of the electronic device is always on, the first processor may determine that the electronic device is in the standby state, and if the indicator light of the electronic device is in the flashing state, the first processor The monitor can determine that the electronic device is in a screen-off state.

S1202、如果电子设备处于熄屏状态，并且无音频音箱业务，则第一处理器控制电子设备从熄屏状态切换至待机状态。S1202. If the electronic device is in the screen-off state and there is no audio speaker service, the first processor controls the electronic device to switch from the screen-off state to the standby state.

结合图6，如S9，电子设备处于熄屏状态，并且电子设备无音频音箱业务，相当于，电子设备既没有播放视频节目，也没有播放音频节目。此时，第一处理器控制电子设备从熄屏状态切换到待机状态，使电子设备中的大部分模块下电，可以极大地降低电子设备的功耗。Combined with Figure 6, for example, S9, the electronic device is in the screen-off state, and the electronic device has no audio speaker service, which is equivalent to the electronic device playing neither video programs nor audio programs. At this time, the first processor controls the electronic device to switch from the screen-off state to the standby state, powering off most modules in the electronic device, which can greatly reduce the power consumption of the electronic device.

可选的，如果电子设备处于熄屏状态，并且有音频音箱业务，相当于电子设备在播放音频节目。此时，第一处理器可以在预设时间段内运行语音唤醒算法来检测音频数据中是否包括唤醒词。如果第一处理器检测到唤醒词，则第一处理器运行语音唤醒算法对音频数据进行语音识别，以执行对应的操作。并且，第一处理器在完成对音频数据的语音识别后，指示功耗较低的第二处理器持续地运行语音唤醒算法来检测唤醒词。如果第一处理器在预设时间段内运行语音唤醒算法未检测到唤醒词，则第一处理器指示功耗较低的第二处理器运行语音唤醒算法来检测音频数据中是否包括唤醒词。这样，第一处理器便不需要再持续地运行语音唤醒算法来检测唤醒词，从而提升了第一处理器的性能，并且降低了第一处理器的功耗。Optional, if the electronic device is in the screen-off state and has the audio speaker service, it is equivalent to the electronic device playing audio programs. At this time, the first processor can run the voice wake-up algorithm within a preset time period to detect whether the audio data includes the wake-up word. If the first processor detects the wake-up word, the first processor runs a voice wake-up algorithm to perform voice recognition on the audio data to perform corresponding operations. Moreover, after completing the speech recognition of the audio data, the first processor instructs the second processor with lower power consumption to continuously run the speech wake-up algorithm to detect the wake-up word. If the first processor runs the voice wake-up algorithm within the preset time period and does not detect the wake-up word, the first processor instructs the second processor with lower power consumption to run the voice wake-up algorithm to detect whether the wake-up word is included in the audio data. In this way, the first processor no longer needs to continuously run the voice wake-up algorithm to detect the wake-up word, thereby improving the performance of the first processor and reducing the power consumption of the first processor.

S1203、当电子设备处于待机状态时，第一处理器控制开关电路导通。S1203. When the electronic device is in the standby state, the first processor controls the switch circuit to turn on.

结合图8，当电子设备处于待机状态时，第一处理器控制开关电路导通，以使电源端通过开关电路向降压电路提供目标电压，降压电路用于对目标电压降压后向音频采集模块供电。这样，当电子设备处于待机状态时，音频采集模块仍然能够采集音频数据。这为电子设备处于待机状态时，具有语音唤醒功能提供了硬件基础。Combined with Figure 8, when the electronic device is in a standby state, the first processor controls the switch circuit to turn on, so that the power supply terminal provides the target voltage to the buck circuit through the switch circuit, and the buck circuit is used to step down the target voltage and then provide audio Power supply to the acquisition module. In this way, when the electronic device is in standby state, the audio collection module can still collect audio data. This provides a hardware foundation for the voice wake-up function when the electronic device is in standby mode.

S1204、第一处理器指示第二处理器检测音频数据中是否包括唤醒词。S1204. The first processor instructs the second processor to detect whether the audio data includes the wake word.

在电子设备处于非下电状态时，为了使电子设备能够随时响应用户的语音唤醒指令，电子设备需要持续检测唤醒词。第二处理器相对于第一处理器而言，功耗较小，因此，结合图6，如S10，第一处理器指示第二处理器检测音频数据中是否包括唤醒词，使第二处理器代替第一处理器持续的运行语音唤醒算法来进行唤醒词检测，不但能够降低第一处理器的功耗，而且能够提升第一处理器的性能。When the electronic device is not powered off, in order for the electronic device to respond to the user's voice wake-up command at any time, the electronic device needs to continuously detect the wake-up word. The second processor consumes less power than the first processor. Therefore, in conjunction with Figure 6, as shown in S10, the first processor instructs the second processor to detect whether the audio data includes the wake word, so that the second processor Instead of the first processor continuously running the voice wake-up algorithm to perform wake-up word detection, it can not only reduce the power consumption of the first processor, but also improve the performance of the first processor.

可选的，为了进一步确保电子设备在处于待机状态时能够低功耗的实现语音唤醒功能，第一处理器指示第二处理器检测音频数据中是否包括唤醒词的过程，具体可以包括：首先，第一处理器获取电子设备的当前功耗；然后，第一处理器将当前功耗与目标功耗进行比较，如果当前功耗小于目标功耗，则第一处理器指示第二处理器检测音频数据中是否包括唤醒词。如果当前功耗大于目标功耗，则第一处理器不会指示第二处理器检测音频数据中是否包括唤醒词，同时第一处理器也不会检测音频数据中是否包括唤醒词。也就是说，如果当前功耗大于目标功耗，则表示本该下电的某些模块没有下电，此时，第一处理器不会指示第二处理器检测音频数据中是否包括唤醒词，同时第一处理器也不会检测音频数据中是否包括唤醒词。因此，如果当前功耗大于目标功耗，第一处理器会禁用语音唤醒功能，并且控制本该下电而没有下电的某些模块下电，直至第一处理器确定电子设备的当前功耗小于目标功耗，才会启用语音唤醒功能，即指示第二处理器检测唤醒词。Optionally, in order to further ensure that the electronic device can realize the voice wake-up function with low power consumption when it is in the standby state, the first processor instructs the second processor to detect whether the audio data includes the wake-up word, which may specifically include: first, The first processor obtains the current power consumption of the electronic device; then, the first processor compares the current power consumption with the target power consumption. If the current power consumption is less than the target power consumption, the first processor instructs the second processor to detect audio Whether the wake word is included in the data. If the current power consumption is greater than the target power consumption, the first processor will not instruct the second processor to detect whether the audio data includes the wake-up word, and the first processor will not detect whether the audio data includes the wake-up word. That is to say, if the current power consumption is greater than the target power consumption, it means that some modules that should be powered off are not powered off. At this time, the first processor will not instruct the second processor to detect whether the audio data includes the wake-up word. At the same time, the first processor will not detect whether the audio data includes the wake word. Therefore, if the current power consumption is greater than the target power consumption, the first processor disables the voice wake-up function and controls some modules that should be powered off but are not powered off until the first processor determines the current power consumption of the electronic device If the power consumption is less than the target power consumption, the voice wake-up function will be enabled, which instructs the second processor to detect the wake-up word.

S1205、第一处理器进入休眠状态。S1205. The first processor enters the sleep state.

第一处理器在指示第二处理器检测音频数据中是否包括唤醒词后，进入休眠状态，能够进一步降低第一处理器的功耗，从而进一步降低电子设备的功耗。After instructing the second processor to detect whether the audio data includes the wake-up word, the first processor enters the sleep state, which can further reduce the power consumption of the first processor, thereby further reducing the power consumption of the electronic device.

S1206、如果第二处理器检测到唤醒词，则第二处理器唤醒第一处理器。S1206. If the second processor detects the wake-up word, the second processor wakes up the first processor.

结合图6，如果第二处理器运行语音唤醒算法检测到唤醒词，如S11，表明有语音唤醒业务，则第二处理器唤醒第一处理器，以便于第一处理器确定具体的语音唤醒业务。Combined with Figure 6, if the second processor runs the voice wake-up algorithm and detects a wake-up word, such as S11, indicating that there is a voice wake-up service, the second processor wakes up the first processor so that the first processor can determine the specific voice wake-up service. .

S1207、第一处理器对音频数据进行语音识别。S1207. The first processor performs speech recognition on the audio data.

第一处理器运行语音唤醒算法对音频数据进行语音识别，确定具体的语音唤醒业务，从而执行对应的操作。第一处理器执行完对应的操作后，电子设备可能处于亮屏状态，或熄屏状态。The first processor runs the voice wake-up algorithm to perform voice recognition on the audio data, determines the specific voice wake-up service, and performs corresponding operations. After the first processor completes the corresponding operation, the electronic device may be in a screen-on state or a screen-off state.

S1208、如果电子设备处于亮屏状态，则第一处理器指示第二处理器检测音频数据中是否包括唤醒词。S1208. If the electronic device is in the screen-on state, the first processor instructs the second processor to detect whether the audio data includes the wake-up word.

当电子设备处于亮屏状态时，为了降低功耗，第一处理器指示第二处理器检测音频数据中是否包括唤醒词，以确定有、无语音唤醒业务。When the electronic device is in the screen-on state, in order to reduce power consumption, the first processor instructs the second processor to detect whether the audio data includes a wake-up word to determine whether there is a voice wake-up service.

S1209、如果第二处理器检测到唤醒词，则第二处理器唤醒第一处理器。S1209. If the second processor detects the wake-up word, the second processor wakes up the first processor.

结合图7，当第二处理器运行语音唤醒算法检测到唤醒词后，如S11，表明有语音唤醒业务，第二处理器唤醒第一处理器，从而使第一处理器运行语音唤醒算法来对音频数据进行语音识别，从而执行对应的操作。如S12，当第一处理器完成语音识别后，此时无语音唤醒业务，第一处理器再次指示第二处理器运行语音唤醒算法检测唤醒词。Combined with Figure 7, when the second processor runs the voice wake-up algorithm and detects the wake-up word, such as S11, indicating that there is a voice wake-up service, the second processor wakes up the first processor, so that the first processor runs the voice wake-up algorithm to deal with the problem. The audio data is used for speech recognition to perform corresponding operations. As in S12, after the first processor completes the speech recognition, there is no voice wake-up service at this time, and the first processor again instructs the second processor to run the voice wake-up algorithm to detect the wake-up word.

S1210、第一处理器对音频数据进行语音识别。S1210. The first processor performs speech recognition on the audio data.

结合图7，当第一处理器检测到唤醒词后，表明此时有语音唤醒业务，第一处理器再运行语音唤醒算法对音频数据进行语音识别，从而执行对应的操作。Referring to Figure 7, when the first processor detects the wake-up word, it indicates that there is a voice wake-up service at this time, and the first processor then runs the voice wake-up algorithm to perform speech recognition on the audio data, thereby performing corresponding operations.

可选的，第一处理器执行完对应的操作后，如果电子设备仍处于亮屏状态，则第一处理器再指示第二处理器检测唤醒词。第一处理器执行完对应的操作后，如果电子设备处于熄屏状态，则第一处理器再根据电子设备有无音频音箱业务，执行上述对应的步骤(如S1202-S1207)。第一处理器执行完对应的操作后，如果电子设备处于待机状态，则第一处理器可以执行上述如S1203-S1207的步骤。Optionally, after the first processor performs the corresponding operation, if the electronic device is still in the screen-on state, the first processor instructs the second processor to detect the wake-up word. After the first processor completes the corresponding operation, if the electronic device is in the screen-off state, the first processor will perform the above corresponding steps (such as S1202-S1207) according to whether the electronic device has the audio speaker service. After the first processor completes the corresponding operation, if the electronic device is in a standby state, the first processor may perform the above-mentioned steps S1203-S1207.

综上所述，本申请实施例提供的语音唤醒电路、方法和电子设备，在电子设备处于亮屏状态、熄屏状态、待机状态下，检测唤醒词的工作是由低功耗的第二处理器来处理的。这样，就可以节约高功耗的第一处理器的资源，从而降低了第一处理器的功耗，并且提升了第一处理器的性能，而第二处理器的功耗较低，可以忽略不计，因此，降低了电子设备的功耗，并且提升了电子设备的性能，而且使电子设备处于亮屏状态、熄屏状态、待机状态下均具有语音唤醒功能。To sum up, in the voice wake-up circuit, method and electronic device provided by the embodiments of the present application, when the electronic device is in the screen-on state, screen-off state, or standby state, the work of detecting the wake-up word is performed by a low-power second process processor to handle. In this way, the resources of the high-power first processor can be saved, thereby reducing the power consumption of the first processor and improving the performance of the first processor, while the power consumption of the second processor is low and can be ignored Regardless, therefore, the power consumption of the electronic device is reduced, the performance of the electronic device is improved, and the electronic device has a voice wake-up function in the screen-on state, screen-off state, and standby state.

如图13所示，本申请实施例还提供一种芯片系统。该芯片系统1300包括至少一个处理器1301和至少一个接口电路1302。至少一个处理器1301和至少一个接口电路1302可通过线路互联。处理器1301用于支持电子设备实现上述方法实施例中的各个步骤，例如图12所示的方法，至少一个接口电路1302可用于从其它装置(例如存储器)接收信号，或者，向其它装置(例如通信接口)发送信号。该芯片系统可以包括芯片，还可以包括其他分立器件。As shown in Figure 13, an embodiment of the present application also provides a chip system. The chip system 1300 includes at least one processor 1301 and at least one interface circuit 1302. At least one processor 1301 and at least one interface circuit 1302 may be interconnected by wires. The processor 1301 is used to support the electronic device to implement various steps in the above method embodiments, such as the method shown in Figure 12. At least one interface circuit 1302 can be used to receive signals from other devices (such as memory), or to other devices (such as memory). communication interface) to send signals. The chip system may include chips and may also include other discrete devices.

本申请实施例还提供一种计算机可读存储介质，该计算机可读存储介质包括指令，当指令在上述电子设备上运行时，使得该电子设备执行上述方法实施例中的各个步骤，例如执行图12所示的方法。Embodiments of the present application also provide a computer-readable storage medium. The computer-readable storage medium includes instructions. When the instructions are run on the above-mentioned electronic device, the electronic device causes the electronic device to perform various steps in the above-mentioned method embodiments, such as executing the steps shown in FIG. The method shown in 12.

本申请实施例还提供一种包括指令的计算机程序产品，当指令在上述电子设备上运行时，使得该电子设备执行上述方法实施例中的各个步骤，例如执行图12所示的方法。An embodiment of the present application also provides a computer program product including instructions. When the instructions are run on the above-mentioned electronic device, the electronic device causes the electronic device to execute each step in the above-mentioned method embodiment, for example, execute the method shown in Figure 12.

关于芯片系统、计算机可读存储介质、计算机程序产品的技术效果参照前面方法实施例的技术效果。Regarding the technical effects of the chip system, computer-readable storage media, and computer program products, refer to the technical effects of the previous method embodiments.

应理解，在本申请的各种实施例中，上述各过程的序号的大小并不意味着执行顺序的先后，各过程的执行顺序应以其功能和内在逻辑确定，而不应对本申请实施例的实施过程构成任何限定。It should be understood that in the various embodiments of the present application, the size of the sequence numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its functions and internal logic, and should not be used in the embodiments of the present application. The implementation process constitutes any limitation.

本领域普通技术人员可以意识到，结合本文中所公开的实施例描述的各示例的模块及算法步骤，能够以电子硬件、或者计算机软件和电子硬件的结合来实现。这些功能究竟以硬件还是软件方式来执行，取决于技术方案的特定应用和设计约束条件。专业技术人员可以对每个特定的应用来使用不同方法来实现所描述的功能，但是这种实现不应认为超出本申请的范围。Those of ordinary skill in the art can appreciate that the modules and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented with electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Skilled artisans may implement the described functionality using different methods for each specific application, but such implementations should not be considered beyond the scope of this application.

所属领域的技术人员可以清楚地了解到，为描述的方便和简洁，上述描述的系统、装置和模块的具体工作过程，可以参考前述方法实施例中的对应过程，在此不再赘述。Those skilled in the art can clearly understand that for the convenience and simplicity of description, the specific working processes of the systems, devices and modules described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be described again here.

在本申请所提供的几个实施例中，应该理解到，所揭露的系统、设备和方法，可以通过其它的方式实现。例如，以上所描述的设备实施例仅仅是示意性的，例如，所述模块的划分，仅仅为一种逻辑功能划分，实际实现时可以有另外的划分方式，例如多个模块或组件可以结合或者可以集成到另一个设备，或一些特征可以忽略，或不执行。另一点，所显示或讨论的相互之间的耦合或直接耦合或通信连接可以是通过一些接口，设备或模块的间接耦合或通信连接，可以是电性，机械或其它的形式。In the several embodiments provided in this application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only illustrative. For example, the division of modules is only a logical function division. In actual implementation, there may be other division methods. For example, multiple modules or components may be combined or can be integrated into another device, or some features can be ignored, or not implemented. On the other hand, the coupling or direct coupling or communication connection between each other shown or discussed may be through some interfaces, indirect coupling or communication connection of devices or modules, which may be in electrical, mechanical or other forms.

所述作为分离部件说明的模块可以是或者也可以不是物理上分开的，作为模块显示的部件可以是或者也可以不是物理模块，即可以位于一个设备，或者也可以分布到多个设备上。可以根据实际的需要选择其中的部分或者全部模块来实现本实施例方案的目的。The modules described as separate components may or may not be physically separated, and the components shown as modules may or may not be physical modules, that is, they may be located on one device, or they may be distributed to multiple devices. Some or all of the modules can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

另外，在本申请各个实施例中的各功能模块可以集成在一个设备中，也可以是各个模块单独物理存在，也可以两个或两个以上模块集成在一个设备中。In addition, each functional module in each embodiment of the present application can be integrated in one device, or each module can exist physically alone, or two or more modules can be integrated in one device.

在上述实施例中，可以全部或部分地通过软件、硬件、固件或者其任意组合来实现。当使用软件程序实现时，可以全部或部分地以计算机程序产品的形式来实现。该计算机程序产品包括一个或多个计算机指令。在计算机上加载和执行计算机程序指令时，全部或部分地产生按照本申请实施例所述的流程或功能。所述计算机可以是通用计算机、专用计算机、计算机网络、或者其他可编程装置。所述计算机指令可以存储在计算机可读存储介质中，或者从一个计算机可读存储介质向另一个计算机可读存储介质传输，例如，所述计算机指令可以从一个网站站点、计算机、服务器或者数据中心通过有线(例如同轴电缆、光纤、数字用户线(digital subscriber line，DSL))或无线(例如红外、无线、微波等)方式向另一个网站站点、计算机、服务器或数据中心进行传输。所述计算机可读存储介质可以是计算机能够存取的任何可用介质或者是包含一个或多个可以用介质集成的服务器、数据中心等数据存储设备。所述可用介质可以是磁性介质(例如，软盘、硬盘、磁带)，光介质(例如，DVD)、或者半导体介质(例如固态硬盘(solid state disk，SSD))等。In the above embodiments, it may be implemented in whole or in part by software, hardware, firmware, or any combination thereof. When implemented using a software program, it may be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When computer program instructions are loaded and executed on a computer, the processes or functions described in the embodiments of the present application are generated in whole or in part. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions may be stored in or transmitted from one computer-readable storage medium to another computer-readable storage medium, for example, the computer instructions may be transferred from a website, computer, server, or data center Transmission to another website, computer, server or data center through wired (such as coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (such as infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium that can be accessed by a computer or include one or more data storage devices such as servers and data centers that can be integrated with the medium. The available media may be magnetic media (eg, floppy disk, hard disk, magnetic tape), optical media (eg, DVD), or semiconductor media (eg, solid state disk (SSD)), etc.

以上所述，仅为本申请的具体实施方式，但本申请的保护范围并不局限于此，任何熟悉本技术领域的技术人员在本申请揭露的技术范围内，可轻易想到变化或替换，都应涵盖在本申请的保护范围之内。因此，本申请的保护范围应以所述权利要求的保护范围为准。The above are only specific embodiments of the present application, but the protection scope of the present application is not limited thereto. Any person familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed in the present application. should be covered by the protection scope of this application. Therefore, the protection scope of this application should be subject to the protection scope of the claims.

Claims (14)

Translated fromChinese

1.一种语音唤醒电路，其特征在于，应用于电子设备，所述电路包括：第一处理器、第二处理器、开关电路、降压电路和音频采集模块；所述第一处理器的功耗大于所述第二处理器的功耗；所述音频采集模块用于采集音频数据；1. A voice wake-up circuit, characterized in that it is applied to electronic equipment, and the circuit includes: a first processor, a second processor, a switch circuit, a buck circuit and an audio collection module; the first processor The power consumption is greater than the power consumption of the second processor; the audio collection module is used to collect audio data;所述开关电路的第一端耦合至所述第一处理器，所述开关电路的第二端用于耦合至电源端，所述开关电路的第三端耦合至所述降压电路的第一端；所述降压电路的第二端耦合至所述音频采集模块；A first terminal of the switching circuit is coupled to the first processor, a second terminal of the switching circuit is coupled to a power supply terminal, and a third terminal of the switching circuit is coupled to the first terminal of the buck circuit. terminal; the second terminal of the buck circuit is coupled to the audio collection module;所述第一处理器用于，当所述电子设备处于待机状态时，控制所述开关电路导通，以使所述电源端通过所述开关电路向所述降压电路提供目标电压，所述降压电路用于对所述目标电压降压后向所述音频采集模块供电，以及，指示所述第二处理器检测所述音频数据中是否包括唤醒词之后进入休眠状态；The first processor is configured to, when the electronic device is in a standby state, control the switch circuit to be turned on so that the power supply terminal provides a target voltage to the voltage reduction circuit through the switch circuit, and the voltage reduction circuit The voltage circuit is used to reduce the target voltage and then supply power to the audio collection module, and instruct the second processor to detect whether the audio data includes a wake-up word and then enter a sleep state;所述第二处理器用于，如果检测到所述唤醒词，则唤醒所述第一处理器；The second processor is configured to wake up the first processor if the wake-up word is detected;所述第一处理器还用于，对所述音频数据进行语音识别。The first processor is also configured to perform speech recognition on the audio data.2.根据权利要求1所述的电路，其特征在于，所述第一处理器具体用于：2. The circuit of claim 1, wherein the first processor is specifically configured to:获取所述电子设备的当前功耗；Obtain the current power consumption of the electronic device;如果所述当前功耗小于目标功耗，则指示所述第二处理器检测所述音频数据中是否包括所述唤醒词。If the current power consumption is less than the target power consumption, the second processor is instructed to detect whether the audio data includes the wake-up word.3.根据权利要求1或2所述的电路，其特征在于，所述第一处理器还用于：3. The circuit according to claim 1 or 2, characterized in that the first processor is also used for:当所述电子设备处于熄屏状态，并且所述电子设备无音频音箱业务时，控制所述电子设备从所述熄屏状态切换至所述待机状态。When the electronic device is in the screen-off state and the electronic device has no audio speaker service, the electronic device is controlled to switch from the screen-off state to the standby state.4.根据权利要求1-3任一项所述的电路，其特征在于，所述第一处理器还用于：4. The circuit according to any one of claims 1-3, characterized in that the first processor is also used for:当所述电子设备处于亮屏状态时，指示所述第二处理器检测所述音频数据中是否包括唤醒词。When the electronic device is in the screen-on state, the second processor is instructed to detect whether the audio data includes a wake-up word.5.根据权利要求1-4任一项所述的电路，其特征在于，所述开关电路包括：第一开关子电路和第二开关子电路；5. The circuit according to any one of claims 1 to 4, characterized in that the switch circuit includes: a first switch sub-circuit and a second switch sub-circuit;所述第一开关子电路的第一端耦合至所述第一处理器，所述第一开关子电路的第二端用于耦合至所述电源端，所述第一开关子电路的第三端耦合至所述第二开关子电路的第一端；A first terminal of the first switching sub-circuit is coupled to the first processor, a second terminal of the first switching sub-circuit is used to couple to the power supply terminal, and a third terminal of the first switching sub-circuit is coupled to the first processor. terminal coupled to the first terminal of the second switch subcircuit;所述第二开关子电路的第二端耦合至所述电源端，所述第二开关子电路的第三端耦合至所述降压电路的第一端；The second terminal of the second switching sub-circuit is coupled to the power terminal, and the third terminal of the second switching sub-circuit is coupled to the first terminal of the buck circuit;所述第一处理器用于，当所述电子设备处于待机状态时，控制所述第一开关子电路导通，以使所述第二开关子电路导通，所述电源端通过所述第二开关子电路向所述降压电路提供所述目标电压。The first processor is configured to, when the electronic device is in a standby state, control the first switch sub-circuit to turn on so that the second switch sub-circuit turns on, and the power end passes through the second switch sub-circuit. A switching subcircuit provides the target voltage to the buck circuit.6.根据权利要求5所述的电路，其特征在于，所述第一开关子电路包括：第一电阻、第二电阻、NPN型三极管和第三电阻；6. The circuit according to claim 5, wherein the first switch sub-circuit includes: a first resistor, a second resistor, an NPN transistor and a third resistor;所述第一电阻的第一端为所述第一开关子电路的第一端，所述第一电阻的第二端为所述第一开关子电路的第二端；所述第二电阻的第一端耦合至所述第一电阻的第一端，所述第二电阻的第二端耦合至所述NPN型三极管的基极；所述NPN型三极管的发射极用于耦合至接地端，所述NPN型三极管的集电极耦合至所述第三电阻的第一端；所述第三电阻的第二端为所述第一开关子电路的第三端；所述第一处理器具体用于：The first end of the first resistor is the first end of the first switch sub-circuit, and the second end of the first resistor is the second end of the first switch sub-circuit; the second end of the second resistor The first terminal is coupled to the first terminal of the first resistor, the second terminal of the second resistor is coupled to the base of the NPN transistor; the emitter of the NPN transistor is used to couple to the ground terminal, The collector of the NPN transistor is coupled to the first end of the third resistor; the second end of the third resistor is the third end of the first switch sub-circuit; the first processor is specifically used At:当所述电子设备处于待机状态时，控制所述NPN型三极管导通。When the electronic device is in a standby state, the NPN transistor is controlled to be turned on.7.根据权利要求5或6所述的电路，其特征在于，所述第二开关子电路包括：第四电阻和P型场效应管；7. The circuit according to claim 5 or 6, characterized in that the second switch sub-circuit includes: a fourth resistor and a P-type field effect transistor;所述第四电阻的第一端为所述第二开关子电路的第一端，所述第四电阻的第二端为所述第二开关子电路的第二端；所述P型场效应管的栅极耦合至所述第四电阻的第一端，所述P型场效应管的源极耦合至所述第四电阻的第二端，所述P型场效应管的漏极耦合至所述降压电路。The first end of the fourth resistor is the first end of the second switch sub-circuit, and the second end of the fourth resistor is the second end of the second switch sub-circuit; the P-type field effect The gate of the tube is coupled to the first end of the fourth resistor, the source of the P-type field effect transistor is coupled to the second end of the fourth resistor, and the drain of the P-type field effect transistor is coupled to The voltage reducing circuit.8.根据权利要求5-7任一项所述的电路，其特征在于，所述降压电路包括：降压器件、第六电阻和第七电阻；8. The circuit according to any one of claims 5-7, characterized in that the voltage-reducing circuit includes: a voltage-reducing device, a sixth resistor and a seventh resistor;所述降压器件的输入端耦合至所述开关电路的第三端，所述降压器件的输出端耦合至所述第六电阻的第一端、所述降压器件的接地端，以及所述音频采集模块；所述降压器件的调整端耦合至所述第六电阻的第二端、所述第七电阻的第一端；所述第七电阻的第二端用于耦合至接地端。The input terminal of the voltage-reducing device is coupled to the third terminal of the switching circuit, and the output terminal of the voltage-reducing device is coupled to the first terminal of the sixth resistor, the ground terminal of the voltage-reducing device, and the The audio acquisition module; the adjustment terminal of the voltage-reducing device is coupled to the second terminal of the sixth resistor and the first terminal of the seventh resistor; the second terminal of the seventh resistor is used to couple to the ground terminal. .9.一种语音唤醒方法，其特征在于，应用于如权利要求1-8任一项所述的语音唤醒电路；所述电路包括：第一处理器、第二处理器、开关电路、降压电路和音频采集模块；所述第一处理器的功耗大于所述第二处理器的功耗；所述音频采集模块用于采集音频数据；所述开关电路的第一端耦合至所述第一处理器，所述开关电路的第二端用于耦合至电源端，所述开关电路的第三端耦合至所述降压电路的第一端；所述降压电路的第二端耦合至所述音频采集模块；所述电源端通过导通后的所述开关电路向所述降压电路提供目标电压，所述降压电路用于对所述目标电压降压后向所述音频采集模块供电；所述方法包括：9. A voice wake-up method, characterized in that it is applied to the voice wake-up circuit according to any one of claims 1 to 8; the circuit includes: a first processor, a second processor, a switch circuit, a voltage reduction circuit, and a first processor. circuit and audio collection module; the power consumption of the first processor is greater than the power consumption of the second processor; the audio collection module is used to collect audio data; the first end of the switch circuit is coupled to the third A processor, the second end of the switching circuit is coupled to the power end, the third end of the switching circuit is coupled to the first end of the buck circuit; the second end of the buck circuit is coupled to The audio acquisition module; the power supply terminal provides a target voltage to the voltage reduction circuit through the switched circuit after being turned on, and the voltage reduction circuit is used to reduce the target voltage and then provide the target voltage to the audio acquisition module. Power supply; the method includes:当所述电子设备处于待机状态时，所述第一处理器控制所述开关电路导通，以及，指示所述第二处理器检测所述音频数据中是否包括唤醒词之后进入休眠状态；When the electronic device is in the standby state, the first processor controls the switch circuit to turn on, and instructs the second processor to detect whether the audio data includes a wake-up word and then enter the sleep state;如果检测到所述唤醒词，则所述第二处理器唤醒所述第一处理器；If the wake word is detected, the second processor wakes up the first processor;所述第一处理器对所述音频数据进行语音识别。The first processor performs speech recognition on the audio data.10.根据权利要求9所述的方法，其特征在于，所述第一处理器指示所述第二处理器检测所述音频数据中是否包括唤醒词，包括：10. The method of claim 9, wherein the first processor instructs the second processor to detect whether the audio data includes a wake word, including:所述第一处理器获取所述电子设备的当前功耗；The first processor obtains the current power consumption of the electronic device;如果所述当前功耗小于目标功耗，则所述第一处理器指示所述第二处理器检测所述音频数据中是否包括唤醒词。If the current power consumption is less than the target power consumption, the first processor instructs the second processor to detect whether the audio data includes a wake word.11.根据权利要求9或10所述的方法，其特征在于，所述方法还包括：11. The method according to claim 9 or 10, characterized in that the method further comprises:当所述电子设备处于熄屏状态，并且所述电子设备无音频音箱业务时，所述第一处理器控制所述电子设备从所述熄屏状态切换至所述待机状态。When the electronic device is in the screen-off state and the electronic device has no audio speaker service, the first processor controls the electronic device to switch from the screen-off state to the standby state.12.根据权利要求9-11任一项所述的方法，其特征在于，所述方法还包括：12. The method according to any one of claims 9-11, characterized in that the method further includes:当所述电子设备处于亮屏状态时，所述第一处理器指示所述第二处理器检测所述音频数据中是否包括所述唤醒词。When the electronic device is in the screen-on state, the first processor instructs the second processor to detect whether the audio data includes the wake-up word.13.一种电子设备，其特征在于，包括如权利要求1-8任一项所述的语音唤醒电路，以及存储器；所述存储器中存储指令，当所述语音唤醒电路中的第一处理器和第二处理器执行所述指令时，如权利要求9-12任一项所述的方法被执行。13. An electronic device, characterized in that it includes the voice wake-up circuit according to any one of claims 1 to 8, and a memory; instructions are stored in the memory, and when the first processor in the voice wake-up circuit When the second processor executes the instructions, the method according to any one of claims 9-12 is executed.14.一种计算机可读存储介质，其特征在于，包括指令，当所述指令在电子设备上执行时，使得所述电子设备执行如权利要求9-12任一项所述的方法。14. A computer-readable storage medium, characterized by comprising instructions that, when executed on an electronic device, cause the electronic device to perform the method according to any one of claims 9-12.