技术领域Technical field
本公开涉及车辆技术领域，尤其涉及一种语音信号处理方法、装置、车辆及存储介质。The present disclosure relates to the field of vehicle technology, and in particular, to a speech signal processing method, device, vehicle and storage medium.
背景技术Background technique
目前，车载蓝牙可以通过无线技术与移动终端建立连接，连接后，用户可以通过车载蓝牙或移动终端进行通话，当通过车载蓝牙通话时，会利用车载蓝牙麦克风采集周围的语音信号，并将采集到的语音信号发送给通话的另一端。然而通过车载蓝牙通话过程中，由于车内环境相对复杂，风切声、引擎声、风扇声、车内乘客说话声将直接影响车载蓝牙通话的通话质量。At present, car Bluetooth can establish a connection with mobile terminals through wireless technology. After connection, users can make calls through car Bluetooth or mobile terminals. When talking through car Bluetooth, the car Bluetooth microphone will be used to collect the surrounding voice signals, and the collected The voice signal is sent to the other end of the call. However, during a car Bluetooth call, due to the relatively complex environment in the car, the sound of wind, engine, fan, and the voices of passengers in the car will directly affect the call quality of the car Bluetooth call.
发明内容Contents of the invention
为克服相关技术中存在的问题，本公开提供一种语音信号处理方法、装置、车辆及存储介质。In order to overcome problems existing in related technologies, the present disclosure provides a voice signal processing method, device, vehicle and storage medium.
根据本公开实施例的第一方面，提供一种语音信号处理方法，应用于车辆，包括：According to a first aspect of an embodiment of the present disclosure, a voice signal processing method is provided, applied to a vehicle, including:
在检测到蓝牙通话时，确定所述车辆内被激活的至少一个音区位置，其中，所述车辆的每个座椅位置对应一个音区位置；When a Bluetooth call is detected, determining at least one activated sound zone position in the vehicle, wherein each seat position of the vehicle corresponds to a sound zone position;
获取所述音区位置的目标语音信号，并确定所述目标语音信号的声源方位；Obtain the target speech signal at the sound zone position, and determine the sound source direction of the target speech signal;
根据所述声源方位确定指向所述声源方位的拾音波束，以通过所述拾音波束收集所述目标语音信号。A pickup beam directed to the sound source direction is determined according to the sound source direction, so as to collect the target speech signal through the sound pickup beam.
可选地，所述确定所述车辆内被激活的至少一个音区位置，包括：Optionally, the determining the location of at least one activated sound zone in the vehicle comprises:
控制车辆的中控面板显示可被激活的音区位置的音区模式，其中，所述音区模式包括全车音区模式和局部音区模式；Controlling the vehicle's central control panel to display a sound zone mode of the sound zone position that can be activated, wherein the sound zone mode includes a full vehicle sound zone mode and a local sound zone mode;
基于用户在所述中控面板上选择的全车音区模式，确定车辆的全部座椅位置为被激活的音区位置；Based on the full vehicle sound zone mode selected by the user on the central control panel, determine all seat positions of the vehicle as activated sound zone positions;
基于用户在所述局部音区模式下选择的座椅位置，确定对应被激活的音区位置。Based on the seat position selected by the user in the local sound zone mode, the corresponding activated sound zone position is determined.
可选地，所述车辆的每个座椅配置有车载蓝牙，所述确定所述车辆内被激活的至少一个音区位置，包括：Optionally, each seat of the vehicle is configured with in-vehicle Bluetooth, and determining the location of at least one activated sound zone in the vehicle includes:
获取已建立蓝牙通话的目标车载蓝牙的蓝牙识别号；Obtain the Bluetooth identification number of the target car Bluetooth that has established a Bluetooth call;
根据所述蓝牙识别号对应的目标座椅，确定被激活的至少一个音区位置。The position of at least one activated sound zone is determined according to the target seat corresponding to the Bluetooth identification number.
可选地，所述确定所述目标语音信号的声源方位，包括：Optionally, determining the sound source direction of the target speech signal includes:
对所述目标语音信号进行方位估计，确定所述目标语音信号的声源方位。The target speech signal is estimated to determine the sound source direction of the target speech signal.
可选地，当所述音区位置包括一个时，所述根据所述声源方位确定指向所述声源方位的拾音波束，包括：Optionally, when the sound zone position includes one, determining the pickup beam directed to the sound source direction according to the sound source direction includes:
根据所述声源方位，基于低旁瓣波束形成所述拾音波束。According to the sound source orientation, the pickup beam is formed based on a low side lobe beam.
可选地，当所述音区位置包括多个时，所述根据所述声源方位确定指向所述声源方位的拾音波束，包括：Optionally, when the sound zone position includes multiple sound zone positions, determining the sound pickup beam pointing to the sound source orientation according to the sound source orientation includes:
根据每个目标语音信号的声源方位，基于自适应波束形成指向对应声源方位的拾音波束。According to the sound source direction of each target speech signal, a sound pickup beam pointing to the corresponding sound source direction is formed based on adaptive beamforming.
可选地，所述根据所述声源方位确定指向所述声源方位的拾音波束之后，所述方法还包括：Optionally, after determining the sound pickup beam directed to the sound source direction according to the sound source direction, the method further includes:
按照设定的时间周期检测所述目标语音信号的声源方位；Detecting the sound source direction of the target voice signal according to a set time period;
当检测到所述目标语音信号的声源方位发生变化时，根据变化后的声源方位，调整指向所述声源方位的拾音波束。When it is detected that the sound source direction of the target speech signal changes, the sound pickup beam directed to the sound source direction is adjusted according to the changed sound source direction.
可选地，所述确定所述目标语音信号的声源方位之前，所述方法还包括：Optionally, before determining the sound source orientation of the target speech signal, the method further includes:
对所述目标语音信号进行回声消除。Perform echo cancellation on the target speech signal.
可选地，所述根据所述声源方位确定指向所述声源方位的拾音波束之后，所述方法还包括：Optionally, after determining the sound pickup beam directed to the sound source direction according to the sound source direction, the method further includes:
对收集的所述目标语音信号进行单通道滤波，以滤除噪音。The collected target speech signal is subjected to single-channel filtering to filter out noise.
根据本公开实施例的第二方面，提供一种语音信号处理装置，应用于车辆，包括：According to a second aspect of the embodiment of the present disclosure, a voice signal processing device is provided, applied to a vehicle, including:
第一确定模块，用于在检测到蓝牙通话时，确定所述车辆内被激活的至少一个音区位置，其中，所述车辆的每个座椅位置对应一个音区位置；A first determination module, configured to determine at least one sound zone position activated in the vehicle when a Bluetooth call is detected, wherein each seat position of the vehicle corresponds to a sound zone position;
第二确定模块，用于获取所述音区位置的目标语音信号，并确定所述目标语音信号的声源方位；The second determination module is used to obtain the target speech signal at the sound zone position and determine the sound source direction of the target speech signal;
拾音模块，用于根据所述声源方位确定指向所述声源方位的拾音波束，以通过所述拾音波束收集所述目标语音信号。A sound pickup module, configured to determine a sound pickup beam directed to the sound source direction according to the sound source direction, so as to collect the target speech signal through the sound pickup beam.
可选地，所述第一确定模块采用如下方式确定所述车辆内被激活的至少一个音区位置：Optionally, the first determination module determines the position of at least one activated sound zone in the vehicle in the following manner:
控制车辆的中控面板显示可被激活的音区位置的音区模式，其中，所述音区模式包括全车音区模式和局部音区模式；The central control panel of the vehicle is controlled to display the sound zone mode of the sound zone position that can be activated, wherein the sound zone mode includes a full vehicle sound zone mode and a local sound zone mode;
基于用户在所述中控面板上选择的全车音区模式，确定车辆的全部座椅位置为被激活的音区位置；Based on the full vehicle sound zone mode selected by the user on the central control panel, determine all seat positions of the vehicle as activated sound zone positions;
基于用户在所述局部音区模式下选择的座椅位置，确定对应被激活的音区位置。Based on the seat position selected by the user in the local sound zone mode, the corresponding activated sound zone position is determined.
可选地，所述车辆的每个座椅配置有车载蓝牙，所述第一确定模块采用如下方式确定所述车辆内被激活的至少一个音区位置：Optionally, each seat of the vehicle is configured with on-board Bluetooth, and the first determination module determines the position of at least one activated sound zone in the vehicle in the following manner:
获取已建立蓝牙通话的目标车载蓝牙的蓝牙识别号；Obtain the Bluetooth identification number of the target car Bluetooth that has established a Bluetooth call;
根据所述蓝牙识别号对应的目标座椅，确定被激活的至少一个音区位置。The position of at least one activated sound zone is determined according to the target seat corresponding to the Bluetooth identification number.
可选地，所述第二确定模块采用如下方式确定所述目标语音信号的声源方位：Optionally, the second determination module determines the sound source direction of the target speech signal in the following manner:
对所述目标语音信号进行方位估计，确定所述目标语音信号的声源方位。The target speech signal is subjected to position estimation to determine the sound source position of the target speech signal.
可选地，当所述音区位置包括一个时，所述第二确定模块采用如下方式根据所述声源方位确定指向所述声源方位的拾音波束：Optionally, when the sound zone position includes one, the second determination module determines the sound pickup beam pointing to the sound source orientation according to the sound source orientation in the following manner:
根据所述声源方位，基于低旁瓣波束形成所述拾音波束。According to the sound source orientation, the pickup beam is formed based on a low side lobe beam.
可选地，当所述音区位置包括多个时，所述第二确定模块采用如下方式根据所述声源方位确定指向所述声源方位的拾音波束：Optionally, when the sound zone positions include multiple locations, the second determination module uses the following method to determine the sound pickup beam directed to the sound source direction according to the sound source direction:
根据每个目标语音信号的声源方位，基于自适应波束形成指向对应声源方位的拾音波束。According to the sound source direction of each target speech signal, a pickup beam directed to the corresponding sound source direction is formed based on the adaptive beam.
可选地，所述根据所述声源方位确定指向所述声源方位的拾音波束之后，所述装置还包括：Optionally, after determining the sound pickup beam directed to the sound source direction according to the sound source direction, the device further includes:
检测模块，用于按照设定的时间周期检测所述目标语音信号的声源方位；A detection module, used to detect the sound source direction of the target speech signal according to a set time period;
调整模块，用于当检测到所述目标语音信号的声源方位发生变化时，根据变化后的声源方位，调整指向所述声源方位的拾音波束。An adjustment module, configured to adjust the pickup beam directed to the sound source direction according to the changed sound source direction when a change in the sound source direction of the target speech signal is detected.
可选地，所述装置还包括：Optionally, the device also includes:
消除模块，用于确定所述目标语音信号的声源方位之前，对所述目标语音信号进行回声消除。A cancellation module, configured to perform echo cancellation on the target speech signal before determining the sound source direction of the target speech signal.
可选地，所述装置还包括：Optionally, the device also includes:
滤波模块，用于根据所述声源方位确定指向所述声源方位的拾音波束之后，对收集的所述目标语音信号进行单通道滤波，以滤除噪音。A filtering module is configured to perform single-channel filtering on the collected target speech signal to filter out noise after determining the sound pickup beam directed to the sound source direction according to the sound source direction.
根据本公开实施例的第三方面，提供一种车辆，包括：According to a third aspect of embodiments of the present disclosure, a vehicle is provided, including:
处理器；processor;
用于存储处理器可执行指令的存储器；Memory used to store instructions executable by the processor;
其中，所述处理器被配置为：实现本公开第一方面所提供的方法的步骤。The processor is configured to: implement the steps of the method provided in the first aspect of the present disclosure.
根据本公开实施例的第四方面，提供一种计算机可读存储介质，其上存储有计算机程序指令，该程序指令被处理器执行时实现本公开第一方面所提供的方法的步骤。According to a fourth aspect of an embodiment of the present disclosure, a computer-readable storage medium is provided, on which computer program instructions are stored. When the program instructions are executed by a processor, the steps of the method provided in the first aspect of the present disclosure are implemented.
本公开的实施例提供的技术方案可以包括以下有益效果：在检测到蓝牙通话，确定车辆内被激活的至少一个音区位置后，通过获取该音区位置的目标语音信号，并根据目标语音信号确定目标语音信号的声源方位，之后根据声源方位确定指向声源方位的拾音波束，根据指向声源方位的拾音波束收集目标语音信号，可提高基于车载蓝牙进行通话的通话质量。The technical solution provided by the embodiments of the present disclosure may include the following beneficial effects: after detecting a Bluetooth call and determining the position of at least one activated sound zone in the vehicle, by acquiring the target voice signal at the sound zone position and determining the sound source orientation of the target voice signal based on the target voice signal, and then determining a pickup beam pointing to the sound source orientation based on the sound source orientation, and collecting the target voice signal based on the pickup beam pointing to the sound source orientation, the call quality based on the in-vehicle Bluetooth can be improved.
应当理解的是，以上的一般描述和后文的细节描述仅是示例性和解释性的，并不能限制本公开。It should be understood that the foregoing general description and the following detailed description are exemplary and explanatory only, and do not limit the present disclosure.
附图说明BRIEF DESCRIPTION OF THE DRAWINGS
此处的附图被并入说明书中并构成本说明书的一部分，示出了符合本公开的实施例，并与说明书一起用于解释本公开的原理。The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the disclosure and together with the description, serve to explain the principles of the disclosure.
图1是根据一示例性实施例示出的一种语音信号处理方法的流程图。Fig. 1 is a flow chart showing a method for processing a speech signal according to an exemplary embodiment.
图2是根据一示例性实施例示出的应用本公开的语音信号处理方法的中控面板显示界面示例图。FIG. 2 is an example diagram of a central control panel display interface using the voice signal processing method of the present disclosure, according to an exemplary embodiment.
图3是根据一示例性实施例示出的应用本公开的语音信号处理方法的车辆的音区位置和车辆设置的麦克风位置的示例图。FIG. 3 is an exemplary diagram showing the sound zone position of a vehicle and the positions of microphones arranged in the vehicle to which the speech signal processing method of the present disclosure is applied according to an exemplary embodiment.
图4是根据一示例性实施例示出的一种语音信号处理装置的框图。Figure 4 is a block diagram of a speech signal processing device according to an exemplary embodiment.
图5是一示例性实施例示出的一种车辆的功能框图示意图。FIG. 5 is a schematic diagram of a functional block diagram of a vehicle according to an exemplary embodiment.
具体实施方式Detailed ways
这里将详细地对示例性实施例进行说明，其示例表示在附图中。下面的描述涉及附图时，除非另有表示，不同附图中的相同数字表示相同或相似的要素。以下示例性实施例中所描述的实施方式并不代表与本公开相一致的所有实施方式。相反，它们仅是与如所附权利要求书中所详述的、本公开的一些方面相一致的装置和方法的例子。Exemplary embodiments will be described in detail herein, examples of which are illustrated in the accompanying drawings. When the following description refers to the drawings, the same numbers in different drawings refer to the same or similar elements unless otherwise indicated. The implementations described in the following exemplary embodiments do not represent all implementations consistent with the present disclosure. Rather, they are merely examples of apparatus and methods consistent with aspects of the disclosure as detailed in the appended claims.
需要说明的是，本申请中所有获取信号、信息或数据的动作都是在遵照所在地国家相应的数据保护法规政策的前提下，并获得由相应装置所有者给予授权的情况下进行的。It should be noted that all actions to obtain signals, information or data in this application are performed under the premise of complying with the corresponding data protection regulations and policies of the country where the location is located, and with authorization from the owner of the corresponding device.
图1是根据一示例性实施例示出的一种语音信号处理方法的流程图，如图1所示，语音信号处理方法用于车辆中，包括以下步骤。Figure 1 is a flow chart of a voice signal processing method according to an exemplary embodiment. As shown in Figure 1, the voice signal processing method is used in a vehicle and includes the following steps.
在步骤S11中，在检测到蓝牙通话时，确定车辆内被激活的至少一个音区位置，其中，车辆的每个座椅位置对应一个音区位置。In step S11, when a Bluetooth call is detected, at least one activated sound zone position in the vehicle is determined, where each seat position of the vehicle corresponds to one sound zone position.
其中，本公开也预先对车辆内部进行音区的划分，例如将车辆的每个座椅位置划分为一个音区，即车辆的每个座椅位置对应一个音区位置。The present disclosure also divides the interior of the vehicle into sound zones in advance, for example, each seat position of the vehicle is divided into a sound zone, that is, each seat position of the vehicle corresponds to a sound zone position.
一种实施方式中，在检测到蓝牙通话时，例如可通过如下方式确定被激活的至少一个音区位置：In one implementation, when a Bluetooth call is detected, the position of at least one activated sound zone may be determined in the following manner, for example:
本公开中，为了准确地确定车辆内被激活的音区位置，避免音区位置误唤醒的情况，一种实施方式中，针对相关技术中车辆的蓝牙系统，本公开中，在检测到蓝牙通话时，可以控制车辆的中控面板显示可被激活的音区位置的音区模式，其中，所述音区模式包括全车音区模式和局部音区模式。基于用户在所述中控面板上选择的全车音区模式，确定车辆的全部座椅位置为被激活的音区位置，基于用户在所述局部音区模式下选择的座椅位置，确定对应被激活的音区位置。In the present disclosure, in order to accurately determine the position of the activated sound zone in the vehicle and avoid the situation of accidentally waking up the sound zone position, in one embodiment, for the Bluetooth system of the vehicle in the related art, in the present disclosure, when a Bluetooth call is detected When , the central control panel of the vehicle can be controlled to display a sound zone mode of a sound zone position that can be activated, where the sound zone mode includes a full-vehicle sound zone mode and a local sound zone mode. Based on the full vehicle sound zone mode selected by the user on the central control panel, all seat positions of the vehicle are determined to be activated sound zone positions, and based on the seat positions selected by the user in the local sound zone mode, the corresponding The activated register position.
图2是根据一示例性实施例示出的应用本公开的语音信号处理方法的中控面板显示界面示例图。FIG. 2 is an example diagram of a central control panel display interface using the voice signal processing method of the present disclosure, according to an exemplary embodiment.
在图2中，中控面板显示的音区模式包括全车音区模式和局部音区模式。In Figure 2, the sound zone modes displayed on the central control panel include the full-vehicle sound zone mode and the local sound zone mode.
其中，局部音区模式中可以被选择具体的座椅位置，座椅位置例如可以包括主驾位置、副驾位置、主驾后位置和副驾后位置四个位置。Among them, a specific seat position can be selected in the local sound zone mode, and the seat position may include, for example, four positions: the main driver's seat, the co-driver's seat, the position behind the main driver's seat, and the position behind the co-driver's seat.
当然根据车辆座椅的布局位置，能够选择的座椅位置还可以有其他的配置，本公开在此不做限定。Of course, depending on the layout position of the vehicle seats, the selectable seat positions may also have other configurations, which are not limited in this disclosure.
为了准确地确定车辆内被激活的音区位置，避免音区位置误唤醒的情况，另一种实施方式中，本公开可预先对车辆的每个座椅配置有车载蓝牙，并预先存储与每个座椅对应的车载蓝牙的蓝牙识别号，并将车载蓝牙的蓝牙识别号与座椅位置一一对应关联。进而，在目标车载蓝牙建立蓝牙通话之后，可获取已建立蓝牙通话的目标车载蓝牙的蓝牙识别号，根据蓝牙识别号对应的目标座椅，确定对应被激活的音区位置。In order to accurately determine the position of the activated sound zone in the vehicle and avoid false awakening of the sound zone position, in another embodiment, the present disclosure can pre-configure each seat of the vehicle with in-vehicle Bluetooth, and pre-store the information related to each seat. The Bluetooth identification number of the in-vehicle Bluetooth corresponding to each seat, and the Bluetooth identification number of the in-vehicle Bluetooth is associated with the seat position in one-to-one correspondence. Furthermore, after the target vehicle-mounted Bluetooth establishes a Bluetooth call, the Bluetooth identification number of the target vehicle-mounted Bluetooth that has established the Bluetooth call can be obtained, and the corresponding activated sound zone position is determined based on the target seat corresponding to the Bluetooth identification number.
在步骤S12中，获取音区位置的目标语音信号，并确定目标语音信号的声源方位。In step S12, the target speech signal at the sound zone position is obtained, and the sound source direction of the target speech signal is determined.
图3是根据一示例性实施例示出的应用本公开的语音信号处理方法的车辆的音区位置和车辆设置的麦克风位置的示例图。3 is an example diagram illustrating the sound zone position of the vehicle and the microphone position installed in the vehicle to which the speech signal processing method of the present disclosure is applied, according to an exemplary embodiment.
在图3中，例如车辆的驾驶室分为四个音区位置，分别是主驾位置区、副驾位置区、主驾后位置区和副驾后位置区。在每个音区均设置有麦克风，其中，每个音区的车载麦克风的布置位置不做具体限制。In Figure 3, for example, the cab of a vehicle is divided into four sound zone positions, namely the main driver position area, the passenger position area, the position area behind the main driver and the position area behind the passenger driver. A microphone is provided in each sound zone, and the placement position of the vehicle-mounted microphone in each sound zone is not specifically limited.
仅作为示例，在图3的主驾位置区的正前方位置设置有麦克风11，副驾位置区的右后方位置设置有麦克风21，主驾后位置的左后方位置设置有麦克风22，副驾后位置的右后方位置设置有麦克风23。As an example only, microphone 11 is arranged in front of the main driver's seat area in Figure 3, microphone 21 is arranged at the right rear position of the passenger driver's seat area, microphone 22 is arranged at the left rear position of the main driver's seat, and microphone 23 is arranged at the right rear position of the passenger driver's seat.
其中，可以将位于主驾位置设置有麦克风11，副驾位置设置有麦克风21，主驾后位置设置有麦克风22和副驾后位置设置有麦克风23，组合成一个或者多个车载麦克风阵列，用以获取音区位置的目标语音信号。Among them, a microphone 11 is provided at the main driver's position, a microphone 21 is provided at the passenger's position, a microphone 22 is provided behind the main driver, and a microphone 23 is provided behind the passenger's driver, to form one or more vehicle-mounted microphone arrays to obtain Target speech signal at voice register position.
一种实施方式中，组成的一个或者多个的车载麦克风阵列可以采集车内所有座位的语音信号，也可以基于预先划定的拾音区，采集车内设定拾音区的语音信号。例如，将麦克风11、麦克风21和麦克风22组成一个麦克风阵列，用于获取主驾位置的语音信号和副驾位置的语音信号。将麦克风23、麦克风21和麦克风22组成一个麦克风阵列，用于获取主驾后位置的语音信号和副驾后位置的语音信号。In one implementation, one or more vehicle-mounted microphone arrays can collect voice signals from all seats in the car, or can collect voice signals from a set pickup area in the car based on a predefined pickup area. For example, microphone 11, microphone 21 and microphone 22 are formed into a microphone array, which is used to obtain the voice signal from the main driver's position and the voice signal from the passenger's position. The microphone 23, the microphone 21 and the microphone 22 form a microphone array for acquiring the voice signal from the position behind the main driver and the voice signal from the position behind the passenger driver.
此外，由于车窗，车门等部分的反射能力比较强，针对目标语音信号会产生回音，因此为了提高车载蓝牙通话的通话质量，本公开在确定目标语音信号的声源方位之前，需要对每个麦克风阵列接收的目标语音信号进行回声消除，以避免多径效应。In addition, due to the relatively strong reflective capabilities of car windows, doors, etc., the target voice signal will produce an echo. Therefore, in order to improve the call quality of the car Bluetooth call, the present disclosure needs to determine the sound source direction of the target voice signal before determining the direction of the source of the target voice signal. The target speech signal received by the microphone array undergoes echo cancellation to avoid multipath effects.
对麦克风阵列接收的目标语音信号进行回声消除(Acoustic EchoCancellation,AEC)时，可通过回声消除算法去除通过车窗车门等反射的回声。其中，回声消除算法例如可以包括最小均方(Least Mean Square,LMS)，归一化LMS(Normalized LMS，NLMS)，递归最小二乘(Recursive Least Square，RLS)，分块频域自适应滤波器(PartitionBlock Frequency Domain Adaptive Filter，PBFDAF)，频域NLMS(Frequency DomainNLMS,FDNLMS)等算法。When performing Acoustic EchoCancellation (AEC) on the target speech signal received by the microphone array, the echoes reflected through car windows, doors, etc. can be removed through the echo cancellation algorithm. Among them, the echo cancellation algorithm may include, for example, Least Mean Square (LMS), Normalized LMS (Normalized LMS, NLMS), Recursive Least Square (RLS), and block frequency domain adaptive filter. (PartitionBlock Frequency Domain Adaptive Filter, PBFDAF), frequency domain NLMS (Frequency DomainNLMS, FDNLMS) and other algorithms.
由于乘客乘坐车辆时，不一定乘客坐姿位于音区位置的中心位置，例如乘客可能会倾斜身子拨打电话，因此需要在激活的音区位置的角度覆盖范围内进行声源方位的估计，确定说话人相对音区位置的中心的具体角度。例如，音区位置的角度覆盖范围的角度方位大概为30°～60°。When a passenger is riding in a vehicle, the passenger's sitting position may not necessarily be at the center of the sound zone. For example, the passenger may lean over to make a phone call. Therefore, it is necessary to estimate the direction of the sound source within the angular coverage of the activated sound zone to determine the specific angle of the speaker relative to the center of the sound zone. For example, the angular direction of the angular coverage of the sound zone is approximately 30° to 60°.
其中，例如可通过如下方式对目标语音信号进行方位估计，确定目标语音信号的声源方位：Among them, for example, the orientation of the target speech signal can be estimated by the following method, and the sound source orientation of the target speech signal can be determined:
其中，对目标语音信号进行方位估计时，可通过例如波束形成技术(ConventionalBeamforming，CBF)、最小方差无失真响应技术(Minimum Variance DistortionlessResponse，MVDR)、多重信号分类算法(Multiple Signal Classification，MUSIC)、压缩感知技术(Compressed Sensing，CS)，在激活的音区位置的角度覆盖范围内进行声源方位的估计，确定说话人相对音区位置的中心的具体角度，即得到目标语音信号的声源方位。Among them, when estimating the direction of the target speech signal, the direction of the sound source can be estimated within the angular coverage range of the activated sound zone position through, for example, conventional beamforming (CBF), minimum variance distortionless response (MVDR), multiple signal classification (MUSIC), and compressed sensing (CS) technology, to determine the specific angle of the speaker relative to the center of the sound zone position, that is, to obtain the direction of the sound source of the target speech signal.
在步骤S13中，根据声源方位确定指向声源方位的拾音波束，以通过拾音波束收集目标语音信号。In step S13, the sound pickup beam directed to the sound source direction is determined according to the sound source direction, so as to collect the target speech signal through the sound pickup beam.
本公开中，为实现各音区位置能够独立地进行人机交互，避免各音区位置的用户语音相互串扰，提高用户的使用体验和驾驶安全性，当音区位置包括一个时，例如可通过如下方式根据声源方位确定指向声源方位的拾音波束：In the present disclosure, in order to enable independent human-computer interaction at each sound zone position, avoid crosstalk between user voices at each sound zone position, and improve the user experience and driving safety, when the sound zone position includes one, for example, through The following method determines the pickup beam pointing to the direction of the sound source according to the direction of the sound source:
根据声源方位，基于低旁瓣波束形成拾音波束，即将拾音波束的波束主瓣指向声源方位，拾音波束的波束旁瓣作为噪声进行抑制。According to the direction of the sound source, the pickup beam is formed based on the low side lobe beam, that is, the main beam of the pickup beam is pointed to the direction of the sound source, and the side lobes of the pickup beam are suppressed as noise.
针对相关技术中的车辆的蓝牙系统，例如在检测到蓝牙通话，控制车辆的中控面板显示可被激活的音区位置的音区模式，基于用户在局部音区模式下选择的主驾位置，确定对应被激活的音区位置为主驾位置。For the Bluetooth system of the vehicle in the related technology, for example, when a Bluetooth call is detected, the central control panel of the vehicle is controlled to display the sound zone mode of the sound zone position that can be activated, based on the main driving position selected by the user in the local sound zone mode, Determine the main driver position corresponding to the activated sound zone.
之后，针对主驾位置，确定主驾位置的说话人相对音区位置的中心的角度(即确定目标语音信号的声源方位)，之后根据声源方位，基于低旁瓣波束形成拾音波束，即将拾音波束的波束主瓣指向主驾位置的声源方位，拾音波束的波束旁瓣作为噪声进行抑制。Then, for the main driving position, determine the angle of the speaker at the main driving position relative to the center of the sound zone (that is, determine the sound source direction of the target speech signal), and then form a pickup beam based on the low side lobe beam according to the sound source direction. That is, the main beam of the sound pickup beam is pointed to the direction of the sound source at the main driver's position, and the side lobes of the sound pickup beam are suppressed as noise.
当音区位置包括多个时，例如可通过如下方式根据声源方位确定指向声源方位的拾音波束：When there are multiple sound zone positions, for example, the pickup beam directed to the sound source direction can be determined according to the sound source direction in the following way:
根据每个目标语音信号的声源方位，基于自适应波束形成指向对应声源方位的拾音波束。According to the sound source direction of each target speech signal, a sound pickup beam pointing to the corresponding sound source direction is formed based on adaptive beamforming.
例如，针对为每个座椅配置蓝牙的车辆，在检测到蓝牙通话时，根据已建立蓝牙通话的目标车载蓝牙的蓝牙识别号，确定蓝牙识别号对应的目标座椅为主驾位置和副驾位置，进而确定被激活的音区位置为主驾位置和副驾位置。For example, for a vehicle that is equipped with Bluetooth for each seat, when a Bluetooth call is detected, the target seats corresponding to the Bluetooth identification numbers are determined to be the driver's seat and the co-driver's seat based on the Bluetooth identification number of the target vehicle's Bluetooth that has established the Bluetooth call, and then the activated sound zone positions are determined to be the driver's seat and the co-driver's seat.
之后，分别针对主驾位置和副驾位置，确定主驾位置的说话人相对音区位置的中心的角度，以及确定副驾位置的说话人相对音区位置的中心的角度之后，根据主驾位置的声源方位和副驾位置的声源方位，基于自适应波束形成指向对应声源方位的拾音波束。After that, for the main driver's position and the passenger's position, the angle of the speaker in the main driver's position relative to the center of the sound zone position is determined, and the angle of the speaker in the passenger's position relative to the center of the sound zone is determined, according to the sound of the main driver's position. The sound source direction of the source and the passenger position are based on the adaptive beam to form a pickup beam pointing to the corresponding sound source direction.
其中，主驾位置的拾音波束的波束主瓣指向主驾位置的声源方位，主驾位置的拾音波束的波束旁瓣为噪声和副驾位置的语音信号，从而指向主驾位置的拾音波束只提取主驾位置的语音信号。副驾位置的拾音波束的波束主瓣指向副驾位置的声源方位，副驾位置的拾音波束的波束旁瓣为噪声和主驾位置的语音信号，从而指向副驾位置的拾音波束只提取副驾位置的语音信号。并且这两个提取过程可以通过多线程同时处理，提高拾音效率。Among them, the main lobe of the pickup beam at the main driver's position points to the direction of the sound source at the main driver's position, and the side lobes of the pickup beam at the main driver's position are noise and the voice signal from the passenger position, thus pointing to the pickup wave at the main driver's position. The beam only extracts the voice signal from the main driver's position. The main lobe of the pickup beam at the passenger position points to the direction of the sound source at the passenger position. The side lobes of the pickup beam at the passenger position are noise and the voice signal from the main driver position. Therefore, the pickup beam directed at the passenger position only extracts the passenger position. voice signal. And these two extraction processes can be processed simultaneously through multi-threading to improve sound pickup efficiency.
此外，由于根据声源方位确定指向声源方位的拾音波束之后，拾音波束并不能完全抑制拾音波束之外的噪音，同时拾音波束的波束主瓣内还会混进噪音，因此为了进一步滤除噪音，提高目标语音信号的信噪比以及蓝牙通话清晰度，本公开在根据声源方位确定指向声源方位的拾音波束之后，语音信号处理方法还包括：In addition, since the pickup beam pointing to the sound source direction is determined according to the direction of the sound source, the pickup beam cannot completely suppress the noise outside the pickup beam. At the same time, noise will be mixed into the main lobe of the pickup beam. Therefore, in order to To further filter out noise and improve the signal-to-noise ratio of the target voice signal and the clarity of Bluetooth calls, the present disclosure determines the pickup beam directed to the direction of the sound source according to the direction of the sound source, and the voice signal processing method also includes:
对收集的目标语音信号进行单通道滤波，以滤除噪音。Perform single-channel filtering on the collected target speech signal to filter out noise.
其中，单通道滤波例如包括谱减法及其改进算法、维纳滤波及其改进算法、小波分解降噪算法、子空间降噪算法。或者采用机器学习算法也可以对收集的目标语音信号进行语音降噪，例如采用深度学习网络滤波技术继续对提取的语音信号进行滤波，提高信噪比，提高通话的清晰度。Among them, single-channel filtering includes, for example, spectral subtraction and its improved algorithm, Wiener filter and its improved algorithm, wavelet decomposition noise reduction algorithm, and subspace noise reduction algorithm. Alternatively, machine learning algorithms can also be used to perform speech denoising on the collected target speech signals. For example, deep learning network filtering technology can be used to continue filtering the extracted speech signals to improve the signal-to-noise ratio and improve the clarity of the call.
机器学习算法例如可以采用循环神经网络(Recurrent Neural Network,RNN)，CLD网络(Convolutional Neural Networks，Long Short-Term Memory，Deep NeuralNetworks)等。或者可以采用多种降噪技术级联组合使用。Machine learning algorithms can use, for example, Recurrent Neural Network (RNN), CLD Network (Convolutional Neural Networks, Long Short-Term Memory, Deep Neural Networks), etc. Or multiple noise reduction technologies can be used in cascade combination.
此外，由于车内用户的坐姿可能会发生变化，且是一个慢变的过程，因此可以设定n秒的时间周期，按照设定的时间周期检测目标语音信号的声源方位，当检测到目标语音信号的声源方位发生变化时，根据变化后的声源方位，调整指向声源方位的拾音波束。In addition, since the sitting posture of the user in the car may change, and it is a slow-changing process, a time period of n seconds can be set, and the sound source direction of the target voice signal is detected according to the set time period. When the target is detected When the sound source direction of the speech signal changes, the pickup beam directed to the sound source direction is adjusted according to the changed sound source direction.
在本公开的示例性实施例中，在检测到蓝牙通话，确定车辆内被激活的至少一个音区位置后，通过获取该音区位置的目标语音信号，并根据目标语音信号确定目标语音信号的声源方位，之后根据声源方位确定指向声源方位的拾音波束，根据指向声源方位的拾音波束收集目标语音信号，可提高基于车载蓝牙进行通话的通话质量。In an exemplary embodiment of the present disclosure, after a Bluetooth call is detected and the position of at least one activated sound zone in the vehicle is determined, the target voice signal at the sound zone position is obtained, and the sound source orientation of the target voice signal is determined based on the target voice signal. Then, a pickup beam pointing to the sound source orientation is determined based on the sound source orientation, and the target voice signal is collected based on the pickup beam pointing to the sound source orientation, thereby improving the call quality based on the in-vehicle Bluetooth.
图4是根据一示例性实施例示出的一种语音信号处理装置400的框图，应用于车辆，参照图4，语音信号处理装置包括：Figure 4 is a block diagram of a voice signal processing device 400 according to an exemplary embodiment, applied to a vehicle. Referring to Figure 4, the voice signal processing device includes:
第一确定模块401，用于在检测到蓝牙通话时，确定所述车辆内被激活的至少一个音区位置，其中，所述车辆的每个座椅位置对应一个音区位置；The first determination module 401 is configured to determine at least one sound zone position activated in the vehicle when a Bluetooth call is detected, wherein each seat position of the vehicle corresponds to a sound zone position;
第二确定模块402，用于获取所述音区位置的目标语音信号，并确定所述目标语音信号的声源方位；The second determination module 402 is used to obtain the target speech signal at the voice zone position and determine the sound source direction of the target speech signal;
拾音模块403，用于根据所述声源方位确定指向所述声源方位的拾音波束，以通过所述拾音波束收集所述目标语音信号。The sound pickup module 403 is configured to determine a sound pickup beam directed to the sound source direction according to the sound source direction, so as to collect the target speech signal through the sound pickup beam.
可选地，所述第一确定模块401采用如下方式确定所述车辆内被激活的至少一个音区位置：Optionally, the first determination module 401 determines the location of at least one activated sound zone in the vehicle in the following manner:
控制车辆的中控面板显示可被激活的音区位置的音区模式，其中，所述音区模式包括全车音区模式和局部音区模式；Controlling the vehicle's central control panel to display a sound zone mode of the sound zone position that can be activated, wherein the sound zone mode includes a full vehicle sound zone mode and a local sound zone mode;
基于用户在所述中控面板上选择的全车音区模式，确定车辆的全部座椅位置为被激活的音区位置；Based on the full-vehicle sound zone mode selected by the user on the central control panel, determining all seat positions of the vehicle as activated sound zone positions;
基于用户在所述局部音区模式下选择的座椅位置，确定对应被激活的音区位置。Based on the seat position selected by the user in the local sound zone mode, the corresponding activated sound zone position is determined.
可选地，所述车辆的每个座椅配置有车载蓝牙，所述第一确定模块401采用如下方式确定所述车辆内被激活的至少一个音区位置：Optionally, each seat of the vehicle is configured with on-board Bluetooth, and the first determination module 401 determines the position of at least one activated sound zone in the vehicle in the following manner:
获取已建立蓝牙通话的目标车载蓝牙的蓝牙识别号；Obtain the Bluetooth identification number of the target car Bluetooth that has established a Bluetooth call;
根据所述蓝牙识别号对应的目标座椅，确定被激活的至少一个音区位置。The position of at least one activated sound zone is determined according to the target seat corresponding to the Bluetooth identification number.
可选地，所述第二确定模块402采用如下方式确定所述目标语音信号的声源方位：Optionally, the second determination module 402 determines the sound source direction of the target speech signal in the following manner:
对所述目标语音信号进行方位估计，确定所述目标语音信号的声源方位。The target speech signal is estimated to determine the sound source direction of the target speech signal.
可选地，当所述音区位置包括一个时，所述第二确定模块402采用如下方式根据所述声源方位确定指向所述声源方位的拾音波束：Optionally, when the sound zone position includes one, the second determination module 402 uses the following method to determine the sound pickup beam directed to the sound source direction according to the sound source direction:
根据所述声源方位，基于低旁瓣波束形成所述拾音波束。According to the sound source orientation, the pickup beam is formed based on a low side lobe beam.
可选地，当所述音区位置包括多个时，所述第二确定模块402采用如下方式根据所述声源方位确定指向所述声源方位的拾音波束：Optionally, when the sound zone positions include multiple locations, the second determination module 402 uses the following method to determine the sound pickup beam directed to the sound source direction according to the sound source direction:
根据每个目标语音信号的声源方位，基于自适应波束形成指向对应声源方位的拾音波束。According to the sound source direction of each target speech signal, a pickup beam directed to the corresponding sound source direction is formed based on the adaptive beam.
可选地，所述根据所述声源方位确定指向所述声源方位的拾音波束之后，所述装置还包括：Optionally, after determining the sound pickup beam directed to the sound source direction according to the sound source direction, the device further includes:
检测模块，用于按照设定的时间周期检测所述目标语音信号的声源方位；A detection module, used to detect the sound source direction of the target speech signal according to a set time period;
调整模块，用于当检测到所述目标语音信号的声源方位发生变化时，根据变化后的声源方位，调整指向所述声源方位的拾音波束。An adjustment module, configured to adjust the pickup beam directed to the sound source direction according to the changed sound source direction when a change in the sound source direction of the target speech signal is detected.
可选地，所述装置还包括：Optionally, the device also includes:
消除模块，用于确定所述目标语音信号的声源方位之前，对所述目标语音信号进行回声消除。A cancellation module, configured to perform echo cancellation on the target speech signal before determining the sound source direction of the target speech signal.
可选地，所述装置还包括：Optionally, the device further comprises:
滤波模块，用于根据所述声源方位确定指向所述声源方位的拾音波束之后，对收集的所述目标语音信号进行单通道滤波，以滤除噪音。The filtering module is used to determine the sound pickup beam pointing to the sound source orientation according to the sound source orientation, and then perform single-channel filtering on the collected target voice signal to filter out noise.
关于上述实施例中的装置，其中各个模块执行操作的具体方式已经在有关该方法的实施例中进行了详细描述，此处将不做详细阐述说明。Regarding the devices in the above embodiments, the specific manner in which each module performs operations has been described in detail in the embodiments related to the method, and will not be described in detail here.
本公开还提供一种计算机可读存储介质，其上存储有计算机程序指令，该程序指令被处理器执行时实现本公开提供的语音信号处理方法的步骤。The present disclosure also provides a computer-readable storage medium on which computer program instructions are stored. When the program instructions are executed by a processor, the steps of the speech signal processing method provided by the present disclosure are implemented.
参阅图5，图5是一示例性实施例示出的一种车辆600的功能框图示意图。车辆600可以被配置为完全或部分自动驾驶模式。例如，车辆600可以通过感知系统620获取其周围的环境信息，并基于对周边环境信息的分析得到自动驾驶策略以实现完全自动驾驶，或者将分析结果呈现给用户以实现部分自动驾驶。Referring to FIG. 5 , FIG. 5 is a functional block diagram of a vehicle 600 shown in an exemplary embodiment. The vehicle 600 may be configured in a fully or partially autonomous driving mode. For example, the vehicle 600 may obtain environmental information about its surroundings through the perception system 620 , and obtain an autonomous driving strategy based on the analysis of the surrounding environmental information to achieve fully autonomous driving, or present the analysis results to the user to achieve partially autonomous driving.
车辆600可包括各种子系统，例如，信息娱乐系统610、感知系统620、决策控制系统630、驱动系统640以及计算平台650。可选的，车辆600可包括更多或更少的子系统，并且每个子系统都可包括多个部件。另外，车辆600的每个子系统和部件可以通过有线或者无线的方式实现互连。Vehicle 600 may include various subsystems, such as infotainment system 610, perception system 620, decision control system 630, drive system 640, and computing platform 650. Optionally, vehicle 600 may include more or fewer subsystems, and each subsystem may include multiple components. In addition, each subsystem and component of vehicle 600 can be interconnected through wired or wireless means.
在一些实施例中，信息娱乐系统610可以包括通信系统611，娱乐系统612以及导航系统613。In some embodiments, infotainment system 610 may include communication system 611 , entertainment system 612 , and navigation system 613 .
通信系统611可以包括无线通信系统，无线通信系统可以直接地或者经由通信网络来与一个或多个设备无线通信。例如，无线通信系统可使用3G蜂窝通信，例如CDMA、EVD0、GSM/GPRS，或者4G蜂窝通信，例如LTE。或者5G蜂窝通信。无线通信系统可利用WiFi与无线局域网(wireless local area network，WLAN)通信。在一些实施例中，无线通信系统可利用红外链路、蓝牙或ZigBee与设备直接通信。其他无线协议，例如各种车辆通信系统，例如，无线通信系统可包括一个或多个专用短程通信(dedicated short range communications，DSRC)设备，这些设备可包括车辆和/或路边台站之间的公共和/或私有数据通信。The communication system 611 may include a wireless communication system that can communicate wirelessly with one or more devices directly or via a communication network. For example, the wireless communication system may use 3G cellular communications, such as CDMA, EVDO, GSM/GPRS, or 4G cellular communications, such as LTE. Or 5G cellular communications. The wireless communication system may communicate with a wireless local area network (WLAN) using WiFi. In some embodiments, the wireless communication system may communicate directly with the device using an infrared link, Bluetooth, or ZigBee. Other wireless protocols, such as various vehicle communication systems, for example, the wireless communication system may include one or more dedicated short range communications (DSRC) devices, which may include public and/or private data communications between vehicles and/or roadside stations.
娱乐系统612可以包括显示设备，麦克风和音响，用户可以基于娱乐系统在车内收听广播，播放音乐；或者将手机和车辆联通，在显示设备上实现手机的投屏，显示设备可以为触控式，用户可以通过触摸屏幕进行操作。The entertainment system 612 may include a display device, a microphone and a speaker. The user can listen to the radio and play music in the car based on the entertainment system; or connect the mobile phone to the vehicle and realize the screen projection of the mobile phone on the display device. The display device may be touch-sensitive. , users can operate by touching the screen.
在一些情况下，可以通过麦克风获取用户的语音信号，并依据对用户的语音信号的分析实现用户对车辆600的某些控制，例如调节车内温度等。在另一些情况下，可以通过音响向用户播放音乐。In some cases, the user's voice signal can be obtained through a microphone, and based on the analysis of the user's voice signal, the user can implement certain controls on the vehicle 600 , such as adjusting the temperature inside the vehicle. In other cases, music can be played to the user through speakers.
导航系统613可以包括由地图供应商所提供的地图服务，从而为车辆600提供行驶路线的导航，导航系统613可以和车辆的全球定位系统621、惯性测量单元622配合使用。地图供应商所提供的地图服务可以为二维地图，也可以是高精地图。The navigation system 613 may include a map service provided by a map provider to provide navigation for the vehicle 600 on a driving route. The navigation system 613 may be used in conjunction with the vehicle's global positioning system 621 and inertial measurement unit 622 . The map service provided by the map supplier can be a two-dimensional map or a high-precision map.
感知系统620可包括感测关于车辆600周边的环境的信息的若干种传感器。例如，感知系统620可包括全球定位系统621(全球定位系统可以是GPS系统，也可以是北斗系统或者其他定位系统)、惯性测量单元(inertial measurement unit，IMU)622、激光雷达623、毫米波雷达624、超声雷达625以及摄像装置626。感知系统620还可包括被监视车辆600的内部系统的传感器(例如，车内空气质量监测器、燃油量表、机油温度表等)。来自这些传感器中的一个或多个的传感器数据可用于检测对象及其相应特性(位置、形状、方向、速度等)。这种检测和识别是车辆600的安全操作的关键功能。Perception system 620 may include several types of sensors that sense information about the environment surrounding vehicle 600 . For example, the sensing system 620 may include a global positioning system 621 (the global positioning system may be a GPS system, a Beidou system or other positioning systems), an inertial measurement unit (IMU) 622, a laser radar 623, and a millimeter wave radar. 624, ultrasonic radar 625 and camera device 626. Sensing system 620 may also include sensors that monitor internal systems of vehicle 600 (eg, in-vehicle air quality monitors, fuel gauges, oil temperature gauges, etc.). Sensor data from one or more of these sensors can be used to detect objects and their corresponding properties (position, shape, orientation, speed, etc.). This detection and identification is a critical function for safe operation of vehicle 600 .
全球定位系统621用于估计车辆600的地理位置。Global positioning system 621 is used to estimate the geographic location of vehicle 600 .
惯性测量单元622用于基于惯性加速度来感测车辆600的位姿变化。在一些实施例中，惯性测量单元622可以是加速度计和陀螺仪的组合。The inertial measurement unit 622 is used to sense changes in the posture of the vehicle 600 based on inertial acceleration. In some embodiments, inertial measurement unit 622 may be a combination of an accelerometer and a gyroscope.
激光雷达623利用激光来感测车辆600所位于的环境中的物体。在一些实施例中，激光雷达623可包括一个或多个激光源、激光扫描器以及一个或多个检测器，以及其他系统组件。LiDAR 623 uses laser light to sense objects in the environment in which vehicle 600 is located. In some embodiments, lidar 623 may include one or more laser sources, laser scanners, and one or more detectors, among other system components.
毫米波雷达624利用无线电信号来感测车辆600的周边环境内的物体。在一些实施例中，除了感测物体以外，毫米波雷达624还可用于感测物体的速度和/或前进方向。Millimeter wave radar 624 utilizes radio signals to sense objects within the surrounding environment of vehicle 600 . In some embodiments, in addition to sensing objects, millimeter wave radar 624 may be used to sense the speed and/or heading of the object.
超声雷达625可以利用超声波信号来感测车辆600周围的物体。The ultrasonic radar 625 can sense objects around the vehicle 600 using ultrasonic signals.
摄像装置626用于捕捉车辆600的周边环境的图像信息。摄像装置626可以包括单目相机、双目相机、结构光相机以及全景相机等，摄像装置626获取的图像信息可以包括静态图像，也可以包括视频流信息。The camera device 626 is used to capture image information of the surrounding environment of the vehicle 600. The camera device 626 may include a monocular camera, a binocular camera, a structured light camera, a panoramic camera, etc. The image information acquired by the camera device 626 may include a static image or video stream information.
决策控制系统630包括基于感知系统620所获取的信息进行分析决策的计算系统631，决策控制系统630还包括对车辆600的动力系统进行控制的整车控制器632，以及用于控制车辆600的转向系统633、油门634和制动系统635。The decision control system 630 includes a computing system 631 for analyzing and making decisions based on the information obtained by the sensing system 620. The decision control system 630 also includes a vehicle controller 632 for controlling the power system of the vehicle 600, and for controlling the steering of the vehicle 600. system 633, throttle 634 and brake system 635.
计算系统631可以操作来处理和分析由感知系统620所获取的各种信息以便识别车辆600周边环境中的目标、物体和/或特征。目标可以包括行人或者动物，物体和/或特征可包括交通信号、道路边界和障碍物。计算系统631可使用物体识别算法、运动中恢复结构(Structure from Motion，SFM)算法、视频跟踪等技术。在一些实施例中，计算系统631可以用于为环境绘制地图、跟踪物体、估计物体的速度等等。计算系统631可以将所获取的各种信息进行分析并得出对车辆的控制策略。Computing system 631 may operate to process and analyze various information acquired by perception system 620 in order to identify targets, objects, and/or features in the environment surrounding vehicle 600 . Targets may include pedestrians or animals, and objects and/or features may include traffic signals, road boundaries, and obstacles. The computing system 631 may use object recognition algorithms, structure from motion (SFM) algorithms, video tracking and other technologies. In some embodiments, computing system 631 may be used to map the environment, track objects, estimate the speed of objects, and the like. The computing system 631 can analyze various acquired information and derive a control strategy for the vehicle.
整车控制器632可以用于对车辆的动力电池和引擎641进行协调控制，以提升车辆600的动力性能。The vehicle controller 632 can be used to coordinate the control of the vehicle's power battery and engine 641 to improve the power performance of the vehicle 600.
转向系统633可操作来调整车辆600的前进方向。例如在一个实施例中可以为方向盘系统。The steering system 633 is operable to adjust the forward direction of the vehicle 600. For example, in one embodiment, it may be a steering wheel system.
油门634用于控制引擎641的操作速度并进而控制车辆600的速度。Throttle 634 is used to control the operating speed of engine 641 and thus the speed of vehicle 600 .
制动系统635用于控制车辆600减速。制动系统635可使用摩擦力来减慢车轮644。在一些实施例中，制动系统635可将车轮644的动能转换为电流。制动系统635也可采取其他形式来减慢车轮644转速从而控制车辆600的速度。Braking system 635 is used to control the deceleration of vehicle 600. Braking system 635 can use friction to slow down wheel 644. In some embodiments, braking system 635 can convert the kinetic energy of wheel 644 into electric current. Braking system 635 can also take other forms to slow down the rotation speed of wheel 644 to control the speed of vehicle 600.
驱动系统640可包括为车辆600提供动力运动的组件。在一个实施例中，驱动系统640可包括引擎641、能量源642、传动系统643和车轮644。引擎641可以是内燃机、电动机、空气压缩引擎或其他类型的引擎组合，例如汽油发动机和电动机组成的混动引擎，内燃引擎和空气压缩引擎组成的混动引擎。引擎641将能量源642转换成机械能量。The drive system 640 may include components that provide powered movement for the vehicle 600. In one embodiment, the drive system 640 may include an engine 641, an energy source 642, a transmission system 643, and wheels 644. The engine 641 may be an internal combustion engine, an electric motor, an air compression engine, or a combination of other types of engines, such as a hybrid engine consisting of a gasoline engine and an electric motor, or a hybrid engine consisting of an internal combustion engine and an air compression engine. The engine 641 converts the energy source 642 into mechanical energy.
能量源642的示例包括汽油、柴油、其他基于石油的燃料、丙烷、其他基于压缩气体的燃料、乙醇、太阳能电池板、电池和其他电力来源。能量源642也可以为车辆600的其他系统提供能量。Examples of energy sources 642 include gasoline, diesel, other petroleum-based fuels, propane, other compressed gas-based fuels, ethanol, solar panels, batteries, and other sources of electricity. Energy source 642 may also provide energy to other systems of vehicle 600 .
传动系统643可以将来自引擎641的机械动力传送到车轮644。传动系统643可包括变速箱、差速器和驱动轴。在一个实施例中，传动系统643还可以包括其他器件，比如离合器。其中，驱动轴可包括可耦合到一个或多个车轮644的一个或多个轴。The transmission system 643 can transmit the mechanical power from the engine 641 to the wheels 644. The transmission system 643 may include a gearbox, a differential, and a drive shaft. In one embodiment, the transmission system 643 may also include other devices, such as a clutch. Among them, the drive shaft may include one or more shafts that can be coupled to one or more wheels 644.
车辆600的部分或所有功能受计算平台650控制。计算平台650可包括至少一个处理器651，处理器651可以执行存储在例如存储器652这样的非暂态计算机可读介质中的指令653。在一些实施例中，计算平台650还可以是采用分布式方式控制车辆600的个体组件或子系统的多个计算设备。Some or all functions of vehicle 600 are controlled by computing platform 650 . Computing platform 650 may include at least one processor 651 that may execute instructions 653 stored in a non-transitory computer-readable medium such as memory 652. In some embodiments, computing platform 650 may also be multiple computing devices that control individual components or subsystems of vehicle 600 in a distributed manner.
处理器651可以是任何常规的处理器，诸如商业可获得的CPU。可替换地，处理器651还可以包括诸如图像处理器(Graphic Process Unit，GPU)，现场可编程门阵列(FieldProgrammable Gate Array，FPGA)、片上系统(Sysem on Chip，SOC)、专用集成芯片(Application Specific Integrated Circuit，ASIC)或它们的组合。尽管图5功能性地图示了处理器、存储器、和在相同块中的计算机的其它元件，但是本领域的普通技术人员应该理解该处理器、计算机、或存储器实际上可以包括可以或者可以不存储在相同的物理外壳内的多个处理器、计算机、或存储器。例如，存储器可以是硬盘驱动器或位于不同于计算机的外壳内的其它存储介质。因此，对处理器或计算机的引用将被理解为包括对可以或者可以不并行操作的处理器或计算机或存储器的集合的引用。不同于使用单一的处理器来执行此处所描述的步骤，诸如转向组件和减速组件的一些组件每个都可以具有其自己的处理器，处理器只执行与特定于组件的功能相关的计算。Processor 651 may be any conventional processor, such as a commercially available CPU. Alternatively, the processor 651 may also include, for example, a graphics processor (Graphic Process Unit, GPU), a field programmable gate array (Field Programmable Gate Array, FPGA), a system on a chip (Sysem on Chip, SOC), an application specific integrated chip (Application Specification). Specific Integrated Circuit, ASIC) or their combination. Although FIG. 5 functionally illustrates a processor, memory, and other elements of a computer in the same block, one of ordinary skill in the art will understand that the processor, computer, or memory may actually include storage that may or may not Multiple processors, computers, or memories within the same physical enclosure. For example, the memory may be a hard drive or other storage medium located in a housing different from the computer. Thus, a reference to a processor or computer will be understood to include a reference to a collection of processors or computers or memories that may or may not operate in parallel. Rather than using a single processor to perform the steps described herein, some components, such as the steering component and the deceleration component, may each have their own processor that only performs calculations related to component-specific functionality.
在本公开实施方式中，处理器651可以执行上述的语音信号处理方法。In the embodiment of the present disclosure, the processor 651 can execute the above-mentioned voice signal processing method.
在此处所描述的各个方面中，处理器651可以位于远离该车辆并且与该车辆进行无线通信。在其它方面中，此处所描述的过程中的一些在布置于车辆内的处理器上执行而其它则由远程处理器执行，包括采取执行单一操纵的必要步骤。In various aspects described herein, processor 651 may be located remotely from the vehicle and in wireless communication with the vehicle. In other aspects, some of the processes described herein are performed on a processor disposed within the vehicle and others are performed by a remote processor, including taking the steps necessary to perform a single maneuver.
在一些实施例中，存储器652可包含指令653(例如，程序逻辑)，指令653可被处理器651执行来执行车辆600的各种功能。存储器652也可包含额外的指令，包括向信息娱乐系统610、感知系统620、决策控制系统630、驱动系统640中的一个或多个发送数据、从其接收数据、与其交互和/或对其进行控制的指令。In some embodiments, the memory 652 may include instructions 653 (e.g., program logic) that may be executed by the processor 651 to perform various functions of the vehicle 600. The memory 652 may also include additional instructions, including instructions to send data to, receive data from, interact with, and/or control one or more of the infotainment system 610, the perception system 620, the decision control system 630, and the drive system 640.
除了指令653以外，存储器652还可存储数据，例如道路地图、路线信息，车辆的位置、方向、速度以及其它这样的车辆数据，以及其他信息。这种信息可在车辆600在自主、半自主和/或手动模式中操作期间被车辆600和计算平台650使用。In addition to instructions 653, memory 652 may store data such as road maps, route information, vehicle location, direction, speed and other such vehicle data, as well as other information. This information may be used by vehicle 600 and computing platform 650 during operation of vehicle 600 in autonomous, semi-autonomous and/or manual modes.
计算平台650可基于从各种子系统(例如，驱动系统640、感知系统620和决策控制系统630)接收的输入来控制车辆600的功能。例如，计算平台650可利用来自决策控制系统630的输入以便控制转向系统633来避免由感知系统620检测到的障碍物。在一些实施例中，计算平台650可操作来对车辆600及其子系统的许多方面提供控制。Computing platform 650 may control functions of vehicle 600 based on inputs received from various subsystems (eg, propulsion system 640, perception system 620, and decision control system 630). For example, computing platform 650 may utilize input from decision control system 630 in order to control steering system 633 to avoid obstacles detected by perception system 620 . In some embodiments, computing platform 650 is operable to provide control of many aspects of vehicle 600 and its subsystems.
可选地，上述这些组件中的一个或多个可与车辆600分开安装或关联。例如，存储器652可以部分或完全地与车辆600分开存在。上述组件可以按有线和/或无线方式来通信地耦合在一起。Alternatively, one or more of these components described above may be installed separately or associated with vehicle 600 . For example, memory 652 may exist partially or completely separate from vehicle 600 . The components described above may be communicatively coupled together in wired and/or wireless manners.
可选地，上述组件只是一个示例，实际应用中，上述各个模块中的组件有可能根据实际需要增添或者删除，图5不应理解为对本公开实施例的限制。Optionally, the above components are just an example. In actual applications, the components in each of the above modules may be added or deleted according to actual needs. Figure 5 should not be understood as limiting the embodiment of the present disclosure.
在道路行进的自动驾驶汽车，如上面的车辆600，可以识别其周围环境内的物体以确定对当前速度的调整。物体可以是其它车辆、交通控制设备、或者其它类型的物体。在一些示例中，可以独立地考虑每个识别的物体，并且基于物体的各自的特性，诸如它的当前速度、加速度、与车辆的间距等，可以用来确定自动驾驶汽车所要调整的速度。An autonomous vehicle traveling on the road, such as vehicle 600 above, can identify objects within its surrounding environment to determine adjustments to its current speed. The objects may be other vehicles, traffic control equipment, or other types of objects. In some examples, each identified object can be considered independently and based on the object's respective characteristics, such as its current speed, acceleration, distance from the vehicle, etc., can be used to determine the speed to which the autonomous vehicle will adjust.
可选地，车辆600或者与车辆600相关联的感知和计算设备(例如计算系统631、计算平台650)可以基于所识别的物体的特性和周围环境的状态(例如，交通、雨、道路上的冰、等等)来预测识别的物体的行为。可选地，每一个所识别的物体都依赖于彼此的行为，因此还可以将所识别的所有物体全部一起考虑来预测单个识别的物体的行为。车辆600能够基于预测的识别的物体的行为来调整它的速度。换句话说，自动驾驶汽车能够基于所预测的物体的行为来确定车辆将需要调整到(例如，加速、减速、或者停止)何种稳定状态。在这个过程中，也可以考虑其它因素来确定车辆600的速度，诸如，车辆600在行驶的道路中的横向位置、道路的曲率、静态和动态物体的接近度等等。Optionally, the vehicle 600 or sensing and computing devices associated with the vehicle 600 (eg, computing system 631, computing platform 650) may operate based on the characteristics of the identified objects and the state of the surrounding environment (eg, traffic, rain, conditions on the road). ice, etc.) to predict the behavior of identified objects. Alternatively, each recognized object depends on the behavior of each other, so it is also possible to predict the behavior of a single recognized object by considering all recognized objects together. The vehicle 600 is able to adjust its speed based on the predicted behavior of the identified objects. In other words, the autonomous vehicle is able to determine what stable state the vehicle will need to adjust to (eg, accelerate, decelerate, or stop) based on the predicted behavior of the object. In this process, other factors may also be considered to determine the speed of the vehicle 600, such as the lateral position of the vehicle 600 in the road on which it is traveling, the curvature of the road, the proximity of static and dynamic objects, and so on.
除了提供调整自动驾驶汽车的速度的指令之外，计算设备还可以提供修改车辆600的转向角的指令，以使得自动驾驶汽车遵循给定的轨迹和/或维持与自动驾驶汽车附近的物体(例如，道路上的相邻车道中的车辆)的安全横向和纵向距离。In addition to providing instructions to adjust the speed of the autonomous vehicle, the computing device may also provide instructions to modify the steering angle of the vehicle 600 so that the autonomous vehicle follows a given trajectory and/or maintains contact with objects in the vicinity of the autonomous vehicle (e.g., , vehicles in adjacent lanes on the road) safe lateral and longitudinal distances.
上述车辆600可以为各种类型的行驶工具，例如，轿车、卡车、摩托车、公共汽车、船、飞机、直升飞机、娱乐车、火车等等，本公开实施例不做特别的限定。The above-mentioned vehicle 600 can be various types of driving tools, such as cars, trucks, motorcycles, buses, boats, airplanes, helicopters, recreational vehicles, trains, etc., and the embodiment of the present disclosure is not particularly limited.
在另一示例性实施例中，还提供一种计算机程序产品，该计算机程序产品包含能够由可编程的装置执行的计算机程序，该计算机程序具有当由该可编程的装置执行时用于执行上述的语音信号处理方法的代码部分。In another exemplary embodiment, a computer program product is also provided, the computer program product comprising a computer program executable by a programmable device, the computer program having a function for performing the above when executed by the programmable device. The code part of the speech signal processing method.
本领域技术人员在考虑说明书及实践本公开后，将容易想到本公开的其它实施方案。本申请旨在涵盖本公开的任何变型、用途或者适应性变化，这些变型、用途或者适应性变化遵循本公开的一般性原理并包括本公开未公开的本技术领域中的公知常识或惯用技术手段。说明书和实施例仅被视为示例性的，本公开的真正范围和精神由下面的权利要求指出。Other embodiments of the disclosure will be readily apparent to those skilled in the art from consideration of the specification and practice of the disclosure. This application is intended to cover any variations, uses, or adaptations of the disclosure that follow the general principles of the disclosure and include common knowledge or customary technical means in the technical field that are not disclosed in the disclosure. . It is intended that the specification and examples be considered as exemplary only, with a true scope and spirit of the disclosure being indicated by the following claims.
应当理解的是，本公开并不局限于上面已经描述并在附图中示出的精确结构，并且可以在不脱离其范围进行各种修改和改变。本公开的范围仅由所附的权利要求来限制。It is to be understood that the present disclosure is not limited to the precise structures described above and illustrated in the accompanying drawings, and various modifications and changes may be made without departing from the scope thereof. The scope of the disclosure is limited only by the appended claims.
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211205023.7ACN117789741A (en) | 2022-09-29 | 2022-09-29 | Voice signal processing method, device, vehicle and storage medium |
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211205023.7ACN117789741A (en) | 2022-09-29 | 2022-09-29 | Voice signal processing method, device, vehicle and storage medium |
| Publication Number | Publication Date |
|---|---|
| CN117789741Atrue CN117789741A (en) | 2024-03-29 |
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211205023.7APendingCN117789741A (en) | 2022-09-29 | 2022-09-29 | Voice signal processing method, device, vehicle and storage medium |
| Country | Link |
|---|---|
| CN (1) | CN117789741A (en) |
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118509765A (en)* | 2024-05-21 | 2024-08-16 | 小米汽车科技有限公司 | Voice processing system, voice processing method, medium, product and equipment |
| CN120015045A (en)* | 2025-02-19 | 2025-05-16 | 广州小鹏汽车科技有限公司 | In-vehicle voice call method, vehicle and computer-readable storage medium |
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118509765A (en)* | 2024-05-21 | 2024-08-16 | 小米汽车科技有限公司 | Voice processing system, voice processing method, medium, product and equipment |
| CN118509765B (en)* | 2024-05-21 | 2025-07-25 | 小米汽车科技有限公司 | Speech processing system, speech processing method, medium, product and apparatus |
| CN120015045A (en)* | 2025-02-19 | 2025-05-16 | 广州小鹏汽车科技有限公司 | In-vehicle voice call method, vehicle and computer-readable storage medium |
| Publication | Publication Date | Title |
|---|---|---|
| US12080160B2 (en) | Feedback performance control and tracking | |
| CN107816976B (en) | Method and device for determining the position of an approaching object | |
| JP6773046B2 (en) | Driving support device, driving support method, and moving object | |
| CN110356401B (en) | Automatic driving vehicle and lane changing control method and system thereof | |
| US20240236599A9 (en) | Sound-Making Apparatus Control Method, Sound-Making System, and Vehicle | |
| CN117789741A (en) | Voice signal processing method, device, vehicle and storage medium | |
| CN115056784B (en) | Vehicle control method, device, vehicle, storage medium and chip | |
| CN112789197A (en) | Automobile windowing noise control system and method and related vehicle-mounted equipment | |
| CN115303238B (en) | Auxiliary braking and whistle method and device, vehicle, readable storage medium and chip | |
| EP4296132B1 (en) | Vehicle control method and apparatus, vehicle, non-transitory storage medium and chip | |
| CN114828131B (en) | Communication method, medium, vehicle-mounted communication system, chip and vehicle | |
| CN117476005A (en) | Roof tent control method, system, vehicle and storage medium based on voice recognition | |
| JP7619295B2 (en) | Vehicle device and information integration method | |
| CN114789723B (en) | Vehicle running control method and device, vehicle, storage medium and chip | |
| CN115051723A (en) | Vehicle-mounted antenna device, vehicle-mounted remote communication terminal, vehicle-mounted communication system and vehicle | |
| CN115082898A (en) | Obstacle detection method, obstacle detection device, vehicle, and storage medium | |
| CN115115356A (en) | Vehicle payment method and device, vehicle, readable storage medium and chip | |
| CN115297434B (en) | Service calling method and device, vehicle, readable storage medium and chip | |
| CN114572219B (en) | Automatic overtaking method and device, vehicle, storage medium and chip | |
| CN115535004B (en) | Distance generation method, device, storage medium and vehicle | |
| CN115447506B (en) | Equipment control method, device, vehicle, medium and chip | |
| CN115257628B (en) | Vehicle control method, device, storage medium, vehicle and chip | |
| CN115447506A (en) | Equipment control method, device, vehicle, medium and chip | |
| CN115179930A (en) | Vehicle control method and device, vehicle and readable storage medium | |
| CN119659325A (en) | Vehicle visual angle map rendering method and device |
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |