技术领域technical field
本发明实施例涉及语音识别领域，特别涉及一种语音信息的播放方法、装置及终端。Embodiments of the present invention relate to the field of voice recognition, and in particular, to a method, device and terminal for playing voice information.
背景技术Background technique
语音信息是用户使用诸如智能手机或者平板电脑等终端进行沟通时常用的信息形式之一。Voice information is one of the commonly used forms of information when users use terminals such as smart phones or tablet computers to communicate.
在相关技术中，当终端中具有两种或两种以上播放组件(比如听筒和扬声器)时，通常允许用户选择通过其中的一个播放组件播放语音信息。具体比如，以智能手机为例，智能手机接收到一条语音信息后，若用户想要通过默认的播放组件(比如扬声器)播放该语音信息，则可以直接点击该语音信息，此时，智能手机通过扬声器播放该语音信息；若用户想要通过非默认的播放组件(比如听筒)播放该语音信息，则可以通过预定操作(比如长按语音信息)呼出操作菜单，并点击菜单中通过听筒进行播放的选项，此时，智能手机通过听筒播放该语音信息。In the related art, when there are two or more playing components (such as earpiece and loudspeaker) in the terminal, the user is generally allowed to choose to play voice information through one of the playing components. For example, take a smart phone as an example. After the smart phone receives a voice message, if the user wants to play the voice message through a default playback component (such as a speaker), he can directly click on the voice message. The speaker plays the voice message; if the user wants to play the voice message through a non-default playback component (such as a handset), he can call out the operation menu through a predetermined operation (such as long pressing the voice message), and click Play through the handset in the menu option, at this time, the smart phone will play the voice message through the earpiece.
相关技术中示出的播放方法，用户每次想要通过非默认播放组件播放语音信息时，都需要通过手动操作的方式选择通过非默认播放组件进行播放的选项，操作过程较为繁琐，且需要消耗一定的操作时间，影响语音信息的播放效率。In the playback method shown in the related art, every time the user wants to play voice information through a non-default playback component, he needs to manually select the option to play through a non-default playback component. The operation process is relatively cumbersome and consumes A certain operating time will affect the playback efficiency of voice information.
发明内容Contents of the invention
为了解决相关技术中用户每次想要通过非默认播放组件播放语音信息时，都需要通过手动操作的方式选择通过非默认播放组件进行播放的选项的问题，本发明实施例提供了一种语音信息的播放的方法、装置及终端。所述技术方案如下：In order to solve the problem in the related art that every time a user wants to play voice information through a non-default playback component, he needs to manually select the option to play through a non-default playback component, the embodiment of the present invention provides a voice information The playing method, device and terminal of the present invention. Described technical scheme is as follows:
第一方面，提供了一种语音信息的播放方法，所述方法包括：In a first aspect, a method for playing voice information is provided, the method comprising:
获取语音信息，所述语音信息是以声音片段的形式进行播放的信息；Acquiring voice information, the voice information is information played in the form of sound clips;
分析所述语音信息，获取所述语音信息的信息特征；Analyzing the voice information to obtain information features of the voice information;
根据所述语音信息的信息特征确定对所述语音信息进行播放的播放组件；determining a playback component for playing the voice information according to the information characteristics of the voice information;
根据确定的所述播放组件播放所述语音信息。Play the voice information according to the determined playing component.
第二方面，提供了一种语音信息的播放装置，所述装置包括：In a second aspect, a device for playing voice information is provided, the device comprising:
获取模块，用于获取语音信息，所述语音信息是以声音片段的形式进行播放的信息；An acquisition module, configured to acquire voice information, where the voice information is played in the form of sound clips;
分析模块，用于分析所述语音信息，获取所述语音信息的信息特征；An analysis module, configured to analyze the voice information and obtain information features of the voice information;
确定模块，用于根据所述语音信息的信息特征确定对所述语音信息进行播放的播放组件；A determining module, configured to determine a playback component for playing the voice information according to the information characteristics of the voice information;
播放模块，用于根据确定的所述播放组件播放所述语音信息。A playing module, configured to play the voice information according to the determined playing component.
第三方面，提供了一种终端，所述终端包括：处理器、与所述处理器相连的存储器，以及存储在所述存储器上的程序指令，所述处理器，用于执行所述程序指令，以实现如第一方面所述的语音信息的播放方法。In a third aspect, a terminal is provided, and the terminal includes: a processor, a memory connected to the processor, and program instructions stored in the memory, and the processor is configured to execute the program instructions , so as to realize the method for playing voice information as described in the first aspect.
第四方面，一种计算机可读介质，其上存储有程序指令，所述程序指令被处理器执行时实现如第一方面所述的语音信息的播放方法。In a fourth aspect, a computer-readable medium stores program instructions thereon, and when the program instructions are executed by a processor, the method for playing voice information as described in the first aspect is implemented.
本发明实施例提供的技术方案带来的有益效果是：The beneficial effects brought by the technical solution provided by the embodiments of the present invention are:
通过获取语音信息，并分析语音信息，获取语音信息的信息特征；根据信息特征确定对该语音信息进行播放的播放组件，使用确定的播放组件播放语音信息；解决了相关技术中用户每次想要通过非默认播放组件播放语音信息时，都需要通过手动操作的方式选择通过非默认播放组件进行播放的选项的问题；由于本发明实施例在播放语音信息前，获取了语音信息的信息特征，并在根据该信息特征确定了播放组件后，直接通过该播放组件播放语音信息。因此，在播放语音信息时，该播放方法无需用户手动去选择播放组件，能够直接使用语音信息的信息特征对应的播放组件播放语音信息；省去了用户在播放语音信息前的选择播放组件的步骤，提高了移动终端在不同使用场景中播放语音信息的效率。By acquiring voice information and analyzing the voice information, the information characteristics of the voice information are obtained; according to the information characteristics, the playback component for playing the voice information is determined, and the determined playback component is used to play the voice information; it solves the problem that the user wants to play every time in the related technology When playing voice information through a non-default playback component, it is necessary to manually select the option to play through a non-default playback component; because the embodiment of the present invention obtains the information characteristics of the voice information before playing the voice information, and After the playing component is determined according to the information feature, the voice information is played directly through the playing component. Therefore, when playing the voice information, the playback method does not require the user to manually select the playback component, and can directly use the playback component corresponding to the information feature of the voice information to play the voice information; the step of selecting the playback component before the user plays the voice information is omitted , improving the efficiency of the mobile terminal in playing voice information in different usage scenarios.
附图说明Description of drawings
为了更清楚地说明本发明实施例中的技术方案，下面将对实施例描述中所需要使用的附图作简单地介绍，显而易见地，下面描述中的附图仅仅是本发明的一些实施例，对于本领域普通技术人员来讲，在不付出创造性劳动的前提下，还可以根据这些附图获得其他的附图。In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings that need to be used in the description of the embodiments will be briefly introduced below. Obviously, the drawings in the following description are only some embodiments of the present invention. For those skilled in the art, other drawings can also be obtained based on these drawings without creative effort.
图1是本发明的一个示例性实施例示出的一种语音信息的播放方法的流程图；Fig. 1 is a flowchart of a method for playing voice information shown in an exemplary embodiment of the present invention;
图2是本发明一个实施例提供的一种语音信息的播放方法的流程图；Fig. 2 is a flow chart of a method for playing voice information provided by an embodiment of the present invention;
图3A是基于图2所示的实施例提供的另一种语音信息的播放方法的流程图；FIG. 3A is a flow chart of another voice information playback method provided based on the embodiment shown in FIG. 2;
图3B是基于图2所示的实施例提供的又一种语音信息的播放方法的流程图；Fig. 3B is a flow chart of another method for playing voice information provided based on the embodiment shown in Fig. 2;
图3C是基于图2所示的实施例提供的又一种语音信息的播放方法的流程图；FIG. 3C is a flow chart of another voice information playback method provided based on the embodiment shown in FIG. 2;
图4本发明一个实施例提供的另一种语音信息的播放方法的流程图；Fig. 4 is a flow chart of another method for playing voice information provided by an embodiment of the present invention;
图5是本发明一个实施例提供的一种语音信息的播放装置的结构方框图；Fig. 5 is a structural block diagram of a device for playing voice information provided by an embodiment of the present invention;
图6是本发明一个实施例提供的另一种语音信息的播放装置的结构方框图；FIG. 6 is a structural block diagram of another voice information playback device provided by an embodiment of the present invention;
图7是本发明一个实施例提供的终端的结构示意图。Fig. 7 is a schematic structural diagram of a terminal provided by an embodiment of the present invention.
具体实施方式detailed description
为使本发明的目的、技术方案和优点更加清楚，下面将结合附图对本发明实施方式作进一步地详细描述。In order to make the object, technical solution and advantages of the present invention clearer, the implementation manner of the present invention will be further described in detail below in conjunction with the accompanying drawings.
在本发明实施例中，语音信息的播放方法可以应用在终端中，该终端包括智能手机、平板电脑、电子书阅读器、MP3播放器(Moving Picture Experts Group Audio LayerIII，动态影像专家压缩标准音频层面3)、MP4(Moving Picture Experts Group AudioLayer IV，动态影像专家压缩标准音频层面4)播放器、膝上型便携计算机和台式计算机等等。可选的，该终端中运行有具备语音信息播放功能的应用(或程序)。其中，该应用可以是社交应用、理财应用、通讯应用、安全应用、购物应用、健康应用等等。In the embodiment of the present invention, the method for playing voice information can be applied in a terminal, and the terminal includes a smart phone, a tablet computer, an e-book reader, an MP3 player (Moving Picture Experts Group Audio LayerIII, moving picture experts compress standard audio layer 3), MP4 (Moving Picture Experts Group AudioLayer IV, moving picture experts compressed standard audio layer 4) player, laptop portable computer and desktop computer, etc. Optionally, the terminal runs an application (or program) capable of playing voice information. Wherein, the application may be a social application, a wealth management application, a communication application, a security application, a shopping application, a health application, and the like.
可选地，在上述终端中，包含有两个播放组件：第一播放组件和第二播放组件。第一播放组件和第二播放组件是两个能够相互独立播放声音的播放组件。其中，终端的第一播放组件和第二播放组件，可以根据终端实际控制的播放组件来确定。比如，当终端是智能手机时，第一播放组件可以是听筒或该手机通过接口连接的外接耳机，第二播放组件可以是扬声器或外置音箱。再比如，当终端是平板电脑时，由于该平板电脑能够控制的播放组件是扬声器和外接耳机，因此可以将该平板电脑的外接耳机设置为第一播放组件，将扬声器设置为第二播放组件。再比如，当终端是MP4播放器时，由于该MP4播放器能够控制的播放组件是外接耳机和外置音箱，因此可以将该MP4播放器的外接耳机设置为第一播放组件，将该MP4播放器通过蓝牙连接的蓝牙音箱(外置音箱)设置为第二播放组件。Optionally, in the above terminal, there are two playback components: a first playback component and a second playback component. The first playback component and the second playback component are two playback components that can play sounds independently of each other. Wherein, the first playback component and the second playback component of the terminal may be determined according to the playback components actually controlled by the terminal. For example, when the terminal is a smart phone, the first playback component may be an earpiece or an external earphone connected to the mobile phone through an interface, and the second playback component may be a speaker or an external sound box. For another example, when the terminal is a tablet computer, since the playback components that the tablet computer can control are speakers and external headphones, the external headphones of the tablet computer can be set as the first playback component, and the speakers can be set as the second playback component. For another example, when the terminal is an MP4 player, since the playback components that the MP4 player can control are external headphones and external speakers, the external headphones of the MP4 player can be set as the first playback component to play the MP4 The Bluetooth speaker (external speaker) connected to the device via Bluetooth is set as the second playback component.
可选地，当上述终端实际控制两个以上的播放组件时，例如终端控制三个或三个以上的播放组件，不同的信息特征可以对应不同的播放组件。比如，当智能手机同时控制听筒、扬声器、蓝牙音箱时，智能手机可以设置上述三种播放组件分别对应三种语音信息的信息特征。当智能手机检测到语音信息的信息特征与预设的语音信息的特征模版匹配时，将该语音信息的特征模版对应的播放组件确定为播放组件，使用确定的播放组件播放该语音信息。Optionally, when the terminal actually controls more than two playback components, for example, the terminal controls three or more playback components, different information features may correspond to different playback components. For example, when the smart phone controls the earpiece, the loudspeaker, and the Bluetooth speaker at the same time, the smart phone can set the above three playback components to correspond to the information characteristics of the three voice information respectively. When the smart phone detects that the information feature of the voice information matches the preset feature template of the voice information, it determines the playback component corresponding to the feature template of the voice information as the playback component, and uses the determined playback component to play the voice information.
请参考图1，其示出了本发明的一个示例性实施例示出的一种语音信息的播放方法的流程图，如图1所示，该语音信息的播放方法可以包括：Please refer to FIG. 1, which shows a flow chart of a method for playing voice information shown in an exemplary embodiment of the present invention. As shown in FIG. 1, the method for playing voice information may include:
步骤101，获取语音信息，该语音信息是以声音片段的形式进行播放的信息。In step 101, voice information is acquired, and the voice information is played in the form of sound clips.
在本发明实施例中，语音信息可以是终端从预设通信设备处接收的语音信息。其中，预设通信设备可以是其它终端，包括智能手机、基站或网关等。例如，终端接收预设通信设备发送的语音信息。该语音信息可以通过社交消息、短信、电子邮件或推送消息等形式展示在智能手机中。In this embodiment of the present invention, the voice information may be voice information received by the terminal from a preset communication device. Wherein, the preset communication device may be other terminals, including smart phones, base stations, or gateways. For example, the terminal receives voice information sent by a preset communication device. The voice information can be displayed in the smart phone through social messages, short messages, emails or push messages.
可选地，终端还可以获取本地已存储的语音信息。当语音信息是终端本地已存储的信息时，该语音信息可以是终端录制的录音或拍摄的视频中的语音。该录音或视频中的语音被记录后，直接保存在终端本地。在此情况下，终端可从本地已存储的信息中获取语音信息。Optionally, the terminal can also acquire locally stored voice information. When the voice information is information stored locally in the terminal, the voice information may be the voice in the recording or the video shot by the terminal. After the voice in the recording or video is recorded, it is directly saved locally on the terminal. In this case, the terminal can obtain voice information from locally stored information.
步骤102，分析语音信息，获取该语音信息的信息特征。Step 102, analyzing the voice information to obtain information features of the voice information.
在本发明实施例中，终端在获取语音信息后，可以使用其中的语音分析功能对该语音信息进行分析，语音分析的方式包括但不限于语音识别以及声纹识别等等。In the embodiment of the present invention, after the terminal acquires the voice information, it can use the voice analysis function therein to analyze the voice information. The voice analysis methods include but not limited to voice recognition and voiceprint recognition.
步骤103，根据语音信息的信息特征确定对语音信息进行播放的播放组件。In step 103, a playback component for playing the voice information is determined according to the information characteristics of the voice information.
步骤104，根据确定的播放组件播放语音信息。Step 104, play the voice information according to the determined playing component.
在本发明实施例中，终端在确定播放组件后，可以根据播放组件的实际形态，确定不同的处理语音信息的方法。比如，播放组件仅包含发声单元，则终端负责将语音信息转换为变化的电流信号，通过变化的电流信号驱动播放组件中的发声单元，将变化的电流信号转化为声音。或者，当播放组件中包含存储芯片和处理芯片时，终端可以直接将语音信息转发给该播放组件，令播放组件通过存储芯片存储该语音信息，并通过处理芯片将语音信息转换为变化的电流信号，以驱动发声单元发出声音。In the embodiment of the present invention, after determining the playing component, the terminal may determine different methods for processing voice information according to the actual form of the playing component. For example, if the playback component only includes a sounding unit, the terminal is responsible for converting voice information into a changing current signal, driving the sounding unit in the playback component through the changing current signal, and converting the changing current signal into sound. Or, when the playback component includes a storage chip and a processing chip, the terminal can directly forward the voice information to the playback component, so that the playback component stores the voice information through the storage chip, and converts the voice information into a changing current signal through the processing chip , to drive the sound unit to make sound.
可选地，当确定的播放组件是终端中内置的播放组件，例如是听筒或扬声器时，终端中的处理器将语音信息解析为变化的电流信号，通过该电流信号直接驱动听筒或扬声器中的发声单元，将变化的电流信号转换为声音。Optionally, when the determined playback component is a built-in playback component in the terminal, such as an earpiece or a speaker, the processor in the terminal parses the voice information into a changing current signal, and directly drives the earphone or speaker in the terminal through the current signal. The sound generating unit converts the changing current signal into sound.
可选地，当确定的播放组件是终端外接的耳机或外置音箱时，例如有线耳机、蓝牙耳机、有线音箱或蓝牙音箱等。终端可以在该播放组件具有存储芯片和处理芯片时，直接将语音信息发送给该播放组件，令播放组件解析并播放该语音信息。Optionally, when the determined playback component is an earphone or an external speaker connected to the terminal, for example, a wired earphone, a Bluetooth earphone, a wired speaker, or a Bluetooth speaker. When the playback component has a storage chip and a processing chip, the terminal can directly send the voice information to the playback component, so that the playback component can analyze and play the voice information.
综上所述，本发明实施例提供的语音信息的播放方法，通过获取语音信息，该语音信息是以声音片段的形式进行播放的信息；分析语音信息，获取该语音信息的信息特征；根据语音信息的信息特征确定对语音信息进行播放的播放组件；根据确定的播放组件播放语音信息；解决了相关技术中用户每次想要通过非默认播放组件播放语音信息时，都需要通过手动操作的方式选择通过非默认播放组件进行播放的选项问题；由于本发明实施例在播放语音信息前，获取了语音信息的信息特征，并在根据该信息特征确定了播放组件后，直接通过该播放组件播放语音信息。因此，在播放语音信息时，该播放方法无需用户手动去选择播放组件，能够直接使用语音信息的信息特征对应的播放组件播放语音信息；省去了用户在播放语音信息前选择播放组件的步骤，提高了移动终端在不同使用场景中播放语音信息的效率。In summary, the method for playing voice information provided by the embodiments of the present invention obtains the voice information, and the voice information is information played in the form of a sound segment; analyzes the voice information to obtain the information characteristics of the voice information; The information characteristics of the information determine the playback component for playing the voice information; play the voice information according to the determined playback component; solve the problem of the need for manual operation every time the user wants to play the voice information through a non-default playback component in the related technology The problem of selecting the option to play through a non-default playback component; because the embodiment of the present invention obtains the information characteristics of the voice information before playing the voice information, and after determining the playback component according to the information characteristics, the voice is played directly through the playback component information. Therefore, when playing the voice information, the playing method does not require the user to manually select the playback component, and can directly use the playback component corresponding to the information feature of the voice information to play the voice information; the user is saved from the step of selecting the playback component before playing the voice information, The efficiency of the mobile terminal playing voice information in different usage scenarios is improved.
在本发明实施例中，当终端对应两种播放组件时，可以通过图2所示的方法来播放语音信息，详述如下。In the embodiment of the present invention, when the terminal corresponds to two playing components, the voice information can be played through the method shown in FIG. 2 , which is described in detail as follows.
请参见图2，其示出了本发明一个实施例提供的一种语音信息的播放方法，该语音信息的播放方法可以包括：Please refer to Fig. 2, which shows a method for playing voice information provided by an embodiment of the present invention, the method for playing voice information may include:
步骤201，接收关系建立指令，关系建立指令用于指示建立特征模版和播放组件之间的对应关系。In step 201, a relationship establishment instruction is received, and the relationship establishment instruction is used to instruct the establishment of a corresponding relationship between a feature template and a playback component.
步骤202，根据关系建立指令建立特征模版和播放组件之间的对应关系。Step 202, establish the corresponding relationship between the feature template and the playback component according to the relationship establishing instruction.
在本发明实施例中，终端在判断信息特征与特征模版是否匹配前，可由用户或者应用设计人员预先设置特征模版，或者，从服务器接收已设置好的特征模版。可选地，该特征模版包括但不限于文本模版和声纹模版。其中，文本模版是至少一个关键词(或称敏感词)，该关键词可以是任意对应有语音的文本，例如，汉语词汇、英语词汇或自造词汇等等。声纹模版是从服务器下载的至少一个声纹，该声纹可以是预设的指定人员的声纹，也可以是指定的人群的声纹。比如，张三的声纹或年轻男性的声纹。In the embodiment of the present invention, before the terminal judges whether the information feature matches the feature template, the user or the application designer can pre-set the feature template, or receive the set feature template from the server. Optionally, the feature template includes but not limited to a text template and a voiceprint template. Wherein, the text template is at least one keyword (or called a sensitive word), and the keyword can be any text corresponding to voice, for example, Chinese vocabulary, English vocabulary or self-made vocabulary and so on. The voiceprint template is at least one voiceprint downloaded from the server, and the voiceprint may be the voiceprint of a preset designated person, or the voiceprint of a designated group of people. For example, the voiceprint of Zhang San or the voiceprint of a young male.
随后，终端根据关系建立指令建立特征模版和播放组件之间的对应关系。关系建立指令可以是终端根据用户在触控屏幕上的操作生成的指令，例如，用户在触控屏幕中选择一个特征模版后，再选择一个播放组件，随后点击匹配按钮。此时，终端会相应的生成一个关系建立指令，该指令用于将特征模版和播放组件建立对应关系。Subsequently, the terminal establishes the corresponding relationship between the feature template and the playback component according to the relationship establishing instruction. The relationship establishment instruction may be an instruction generated by the terminal according to the user's operation on the touch screen. For example, the user selects a feature template on the touch screen, then selects a playback component, and then clicks a matching button. At this point, the terminal will correspondingly generate a relationship establishing instruction, which is used to establish a corresponding relationship between the feature template and the playback component.
步骤203，获取语音信息，该语音信息是以声音片段的形式进行播放的信息。Step 203, acquire voice information, where the voice information is played in the form of sound clips.
其中，步骤203的执行方式和步骤101的执行方式相同，详情请参见步骤101的执行过程，此处不再展开论述。Wherein, the execution method of step 203 is the same as the execution method of step 101, please refer to the execution process of step 101 for details, and will not be further discussed here.
步骤204，分析语音信息，获取该语音信息的信息特征。Step 204, analyzing the voice information to obtain information features of the voice information.
可选地，分析功能包括但不限于语音识别和声纹识别，相应的语音信息的信息特征可以是语音文本或声纹特征。Optionally, the analysis function includes but is not limited to speech recognition and voiceprint recognition, and the information features of the corresponding voice information may be speech text or voiceprint features.
可选地，步骤204可被步骤2041、步骤2042或步骤2043替换执行。Optionally, step 204 may be replaced by step 2041 , step 2042 or step 2043 .
步骤2041，对语音信息进行语音识别，获得语音信息对应的语音文本。Step 2041, perform voice recognition on the voice information, and obtain the voice text corresponding to the voice information.
步骤2042，对语音信息进行声纹识别，获得语音信息的声纹特征。Step 2042, performing voiceprint recognition on the voice information to obtain voiceprint features of the voice information.
步骤2043，对语音信息进行语音识别和声纹识别，获取语音信息对应的语音文本以及声纹特征。Step 2043, perform voice recognition and voiceprint recognition on the voice information, and acquire voice text and voiceprint features corresponding to the voice information.
步骤205，判断信息特征与特征模版是否匹配。Step 205, judging whether the information feature matches the feature template.
在本发明实施例中，由于信息特征可以是语音文本或声纹特征。因此，步骤205也相应地可被步骤2051、步骤2052或步骤2053替换执行。In the embodiment of the present invention, the information feature may be a speech text or a voiceprint feature. Therefore, step 205 can also be replaced by step 2051 , step 2052 or step 2053 accordingly.
步骤2051，判断语音文本和文本模版是否匹配。Step 2051, judging whether the voice text matches the text template.
步骤2052，判断声纹特征和声纹模版是否匹配。Step 2052, judging whether the voiceprint feature matches the voiceprint template.
步骤2053，判断信息特征中的语音文本与文本模版，以及，信息特征中的声纹特征与声纹模版是否匹配。Step 2053, judging whether the voice text in the information feature matches the text template, and whether the voiceprint feature in the information feature matches the voiceprint template.
可选地，当步骤204被步骤2041替换，步骤205被步骤2051替换，本发明实施例可执行如图3A所示的一种语音信息的播放方法的流程。Optionally, when step 204 is replaced by step 2041 and step 205 is replaced by step 2051, the embodiment of the present invention may execute a flow of a method for playing voice information as shown in FIG. 3A .
可选地，当步骤204被步骤2042替换，步骤205被步骤2052替换，本发明实施例可执行如图3B所示的一种语音信息的播放方法的流程。Optionally, when step 204 is replaced by step 2042, and step 205 is replaced by step 2052, this embodiment of the present invention may execute a flow of a method for playing voice information as shown in FIG. 3B.
可选地，当步骤204被步骤2043替换，步骤205被步骤2053替换，本发明实施例可执行如图3C所示的一种语音信息的播放方法的流程。Optionally, when step 204 is replaced by step 2043 and step 205 is replaced by step 2053, the embodiment of the present invention may execute a flow of a method for playing voice information as shown in FIG. 3C .
在图3C所示的语音信息的播放方法中，终端在执行完成步骤2053后，执行步骤206或者步骤207。In the voice information playing method shown in FIG. 3C , the terminal executes step 206 or step 207 after completing step 2053 .
步骤206，当语音文本和文本模版匹配，且声纹特征和声纹模版匹配时，确定对语音信息进行播放的播放组件为第一播放组件。Step 206, when the voice text matches the text template, and the voiceprint feature matches the voiceprint template, determine that the playback component that plays the voice information is the first playback component.
步骤207，当语音文本和文本模版不匹配，或声纹特征和声纹模版不匹配时，确定对语音信息进行播放的播放组件为第二播放组件。Step 207, when the voice text does not match the text template, or the voiceprint feature does not match the voiceprint template, determine that the playback component that plays the voice information is the second playback component.
其中，当本发明实施例中所示的图3C中的语音信息方法被执行时，在语音文本和声纹特征均匹配的情况下，终端将第一播放组件确定为播放该语音信息的播放组件。否则，终端将第二播放组件确定为播放该语音信息的播放组件。Wherein, when the voice information method in FIG. 3C shown in the embodiment of the present invention is executed, in the case that the voice text and the voiceprint features both match, the terminal determines the first playback component as the playback component for playing the voice information . Otherwise, the terminal determines the second playback component as the playback component for playing the voice information.
为了使本发明实施例中的特征模版更易理解，下面通过表一来示意性说明一种特征模版可能实现的方式。In order to make the feature template in the embodiment of the present invention easier to understand, Table 1 below schematically illustrates a possible implementation manner of the feature template.
表一Table I
其中，在表一所示的特征模版中，包括文本模版和声纹模版两部分。步骤205执行的判断信息特征与特征模版是否匹配的步骤，可以是在信息特征和特征模版中的一项或多项完全相同时，认为信息特征和特征模版匹配。需要特别说明的是，上述特征模版除了可以同时包括文本模版和声纹模版，还可以仅包含文本模版或仅包含声纹模版。Wherein, the feature templates shown in Table 1 include two parts: a text template and a voiceprint template. The step of judging whether the information feature matches the feature template performed in step 205 may be that the information feature matches the feature template when one or more of the information features and the feature template are identical. It should be noted that, in addition to the above-mentioned feature templates including both text templates and voiceprint templates, they can also include only text templates or only voiceprint templates.
可选地，信息特征除了在和特征模版中的一项或者多项完全相同时，认为和特征模版匹配。信息特征还可以在与特征模版模糊匹配时，被视为与特征模版匹配。Optionally, the information feature is considered to match the feature template unless it is identical to one or more items in the feature template. Informative features can also be considered as matching feature templates when fuzzy matching with feature templates.
例如，请参见表二，其示出了一种预设的模糊匹配模版。For example, please refer to Table 2, which shows a preset fuzzy matching template.
表二Table II
其中，表二中右侧的“信息特征”对应的列中的每一项都是语音信息中的信息特征。当语音信息中包含表二中的信息特征时，认为该语音信息和特征模版模糊匹配。Wherein, each item in the column corresponding to the "information feature" on the right side in Table 2 is an information feature in the voice information. When the voice information contains the information features in Table 2, it is considered that the voice information and the feature template fuzzy match.
可选地，当该信息特征是文本特征时，该信息特征可以是通过语义匹配对应于特征模版中的“特征模版”，例如“账户/帐户”与语义相同的“账目”、“户头”和“账号/帐号”相匹配。可选地，该信息特征也可以通过近音字匹配，例如“张三”与“张山”相匹配。可选地，该信息特征还可以被拆分为单个的字，当拆分后的单个的字依序出现在特征模版中时，认为信息特征和特征模版相匹配。例如，信息特征“美利坚合众国”和特征模版“美国”相匹配。Optionally, when the information feature is a text feature, the information feature can correspond to the "feature template" in the feature template through semantic matching, for example, "account/account" has the same semantics as "account", "account" and "Account/Account" matches. Optionally, the information features can also be matched by close phonetic characters, for example, "Zhang San" is matched with "Zhang Shan". Optionally, the information feature can also be split into individual characters, and when the split individual characters appear in the feature template in sequence, the information feature is considered to match the feature template. For example, the info feature "United States of America" matches the feature template "United States".
可选地，当声纹模版特征需要进行模糊匹配时，采取降低匹配阈值的方式进行匹配。例如，当信息特征的声纹和声纹模版的相似度不小于98％时，认为信息特征和声纹模版相同。当信息特征的声纹和声纹模版的相似度不小于85％且小于98％时，认为信息特征和声纹模版模糊匹配。Optionally, when the features of the voiceprint template need to be fuzzy matched, the matching is performed by lowering the matching threshold. For example, when the similarity between the voiceprint of the information feature and the voiceprint template is not less than 98%, it is considered that the information feature and the voiceprint template are the same. When the similarity between the voiceprint of the information feature and the voiceprint template is not less than 85% and less than 98%, it is considered that the information feature and the voiceprint template are fuzzily matched.
步骤2061，当信息特征与特征模版匹配时，确定对语音信息进行播放的播放组件为第一播放组件。Step 2061, when the information feature matches the feature template, determine the playback component that plays the voice information as the first playback component.
步骤2071，当信息特征与特征模版不匹配时，确定对语音信息进行播放的播放组件为第二播放组件。Step 2071, when the information feature does not match the feature template, determine the playback component that plays the voice information as the second playback component.
在本发明实施例中，第一播放组件和第二播放组件是能够相互独立播放声音的播放组件。可选地，在第一播放组件包括听筒或外接耳机时，第二播放组件包括扬声器或外置音箱。可选地，在第一播放组件包括扬声器或外置音箱时，第二播放组件包括听筒或外接耳机。In the embodiment of the present invention, the first playback component and the second playback component are playback components that can play sounds independently of each other. Optionally, when the first playback component includes an earpiece or an external earphone, the second playback component includes a speaker or an external sound box. Optionally, when the first playback component includes a speaker or an external sound box, the second playback component includes an earpiece or an external earphone.
可选地，当信息特征是语音文本时，信息特征和特征模版匹配的含义是语音文本和文本模版匹配；信息特征和特征模版不匹配的含义是语音文本和文本模版不匹配。Optionally, when the information feature is a speech text, matching the information feature with the feature template means that the speech text matches the text template; the mismatching between the information feature and the feature template means that the speech text does not match the text template.
可选地，当信息特征是声纹特征时，信息特征和特征模版匹配的含义是声纹特征和声纹模版匹配；信息特征和特征模版不匹配的含义是声纹特征和声纹模版不匹配。Optionally, when the information feature is a voiceprint feature, the matching of the information feature and the feature template means that the voiceprint feature matches the voiceprint template; the mismatch between the information feature and the feature template means that the voiceprint feature does not match the voiceprint template .
步骤208，对应语音信息展示提示信息，该提示信息用于指示播放语音信息所使用的播放组件。Step 208, display prompt information corresponding to the voice information, and the prompt information is used to indicate the playback component used to play the voice information.
在本发明实施例中，为了保证用户能够不遗漏地从播放组件中收听到语音信息。终端可以在需要的时候展示提示信息，例如，终端可以在确定播放组件是听筒或者外接耳机等用户有可能听不到声音的播放组件时，在终端屏幕中展示一条提示信息，该提示信息可以是一段文字或者包含图示的文字。例如，一段文字“当前播放组件为听筒，请使用听筒收听语音信息”。In the embodiment of the present invention, in order to ensure that the user can listen to the voice information from the playback component without omission. The terminal can display prompt information when needed. For example, the terminal can display a prompt message on the terminal screen when it determines that the playback component is a playback component such as a receiver or an external earphone that the user may not be able to hear. The prompt message can be A piece of text or text containing an icon. For example, a piece of text "The current playback component is the earpiece, please use the earpiece to listen to voice information".
步骤209，根据确定的播放组件播放语音信息。Step 209, play the voice information according to the determined playing component.
可选地，需要特别说明的是，在终端和外接耳机连接时(包括有线耳机和无线耳机)，终端可以不执行步骤209之前的步骤，将语音信息直接通过外接耳机播放。Optionally, it should be noted that when the terminal is connected to an external earphone (including wired earphones and wireless earphones), the terminal may not perform the steps before step 209, and directly play the voice information through the external earphone.
步骤209的执行方式与步骤104的执行方式相同，详情可参见步骤104的执行方式，此处不再赘述。The execution method of step 209 is the same as the execution method of step 104. For details, please refer to the execution method of step 104, which will not be repeated here.
通过上述公开的内容可知，图2所示语音信息的播放方法可在不同的场景中具体实现为至少三种方法。其中，上述三种方法分别通过图3A、图3B和图3C示出了执行流程。为了进一步展示各个方法可以使用的场景，下面通过具体的应用场景来举例说明图3A、图3B和图3C所示的语音信息的播放方法。It can be known from the above disclosure that the method for playing the voice information shown in FIG. 2 can be implemented in at least three ways in different scenarios. Wherein, the above three methods respectively show the execution flow through FIG. 3A , FIG. 3B and FIG. 3C . In order to further demonstrate the scenarios in which each method can be used, the methods for playing voice information shown in FIG. 3A , FIG. 3B , and FIG. 3C are illustrated below through specific application scenarios.
比如，以终端是智能手机为例，对图3A所示的方法流程进行说明。用户在触控屏幕上进行关系建立操作，将文本模版“张三”与听筒建立对应关系。智能手机的处理器接收相应产生的关系建立指令。处理器根据该关系建立指令建立上述对应关系。当智能手机接收到其它终端发送来的语音信息时，对该语音信息进行语音识别，例如该语音信息对应的文本是“晚上张三叫咱们去吃宵夜，一起去吗”。智能手机的分析算法可以从该识别后的文本中提取出关键词“晚上”、“张三”、“咱们”、“宵夜”、“一起”、“叫”、“吃”、“去”、“吗”，智能手机随后将判断上述关键词中是否存在和文本模版相同的词，经过比对分析后，发现在上述关键词中存在和文本模版“张三”相同的关键词。于是，智能手机确定与该文字模版“张三”对应的听筒为播放该语音信息的播放组件。此时，智能手机可以在用户点击该条语音信息时，直接通过听筒播放该语音信息。与此同时，为了防止用户因不知道该语音信息是通过听筒播放而漏听，智能手机可以在播放语音信息前通过屏幕显示“当前播放组件为听筒，请使用听筒收听语音信息”，当听筒旁边的距离传感器检测到用户将手机放到耳边时，手机将开始播放该语音信息。在图3A所示的应用场景中，当智能手机检测到语音信息中不包含与预设的文本模版匹配的关键词时，智能手机将使用扬声器播放该语音信息。For example, taking the terminal being a smart phone as an example, the flow of the method shown in FIG. 3A is described. The user performs a relationship establishment operation on the touch screen, and establishes a corresponding relationship between the text template "Zhang San" and the receiver. The processor of the smartphone receives correspondingly generated relationship establishment instructions. The processor establishes the above corresponding relationship according to the relationship establishing instruction. When the smart phone receives the voice information sent by other terminals, it performs voice recognition on the voice information, for example, the text corresponding to the voice information is "Zhang San asked us to have a late-night snack, shall we go together?". The analysis algorithm of the smart phone can extract the keywords "evening", "Zhang San", "we", "snack", "together", "call", "eat", "go" from the recognized text , "?", the smartphone will then determine whether there are words identical to the text template in the above keywords. After comparison and analysis, it is found that there are keywords identical to the text template "Zhang San" among the above keywords. Therefore, the smart phone determines that the earpiece corresponding to the text template "Zhang San" is the playback component for playing the voice information. At this time, the smart phone can directly play the voice message through the earpiece when the user clicks on the piece of voice message. At the same time, in order to prevent users from missing the voice message because they do not know that the voice message is played through the earpiece, the smart phone can display "the current playback component is the earpiece, please use the earpiece to listen to the voice message" on the screen before playing the voice message. When the proximity sensor detects that the user puts the mobile phone to the ear, the mobile phone will start to play the voice message. In the application scenario shown in FIG. 3A , when the smart phone detects that the voice information does not contain keywords matching the preset text template, the smart phone will use the speaker to play the voice information.
再比如，以终端是平板电脑为例，对图3B所示的方法流程进行说明。其中，该平板电脑的硬件组件中由于没有安装听筒这一组件，且能够控制的播放组件仅有扬声器和外接耳机，因此，该平板电脑将外接耳机确定为第一播放组件，将扬声器确定为第二播放组件。平板电脑在连接到互联网中的服务器时，可从服务器中下载声纹模版。例如，张三的声纹模版。当平板电脑接收到一条语音信息后，平板电脑对该语音信息进行声纹识别，当识别得到的声纹特征和上述声纹模版匹配时，平板电脑在用户要播放该语音信息时，通过外接耳机播放该语音信息。若平板电脑检测到此时未与外接耳机相连接，则显示提示信息“该语音信息需使用外接耳机播放，未检测到外接耳机，是否改为扬声器播放”，如果用户选择使用扬声器播放，则平板电脑还可以降低扬声器的播放音量来播放该语音信息。当识别得到的声纹特征和上述声纹模版不匹配时，平板电脑在用户要播放该语音信息时，通过扬声器播放该语音信息。For another example, taking the terminal as an example of a tablet computer, the flow of the method shown in FIG. 3B will be described. Among the hardware components of the tablet computer, since the earpiece is not installed, and the playback components that can be controlled are only the speaker and the external earphone, the tablet computer determines the external earphone as the first playback component, and the speaker as the second playback component. Two playback components. When the tablet computer is connected to the server in the Internet, it can download the voiceprint template from the server. For example, Zhang San's voiceprint template. When the tablet computer receives a piece of voice information, the tablet computer performs voiceprint recognition on the voice information, and when the recognized voiceprint features match the above-mentioned voiceprint template, the tablet computer uses an external earphone when the user wants to play the voice information. Play the voice message. If the tablet PC detects that it is not connected to an external headset at this time, it will display a prompt message "This voice message needs to be played with an external headset. No external headset is detected. Do you want to play it with a speaker?" If the user chooses to use the speaker to play, the tablet will The computer can also lower the playback volume of the speaker to play the voice message. When the recognized voiceprint feature does not match the voiceprint template, the tablet computer plays the voice information through the speaker when the user wants to play the voice information.
再比如，仍以终端是智能手机为例，对图3C所示的方法流程进行说明。其中，第一播放组件是听筒，第二播放组件是扬声器。在图3C中智能手机将在语音信息中的声纹特征符合声纹模版，且语音信息中的语音文本和文本模版匹配时，使用第一播放组件播放该语音信息。在不满足上述两个条件中任意一个条件时，使用第二播放组件播放该语音信息。智能手机先通过用户的关系设置信息，建立文本模版和第一播放组件的对应关系，如将文本模版“钱”与听筒建立对应关系。同时从服务器下载要使用的声纹模版，如李四的声纹模版。当智能手机从本地的录音中或接收到的信息中，检测到的声纹特征和李四的声纹模版匹配，且检测到的语音文本和文本模版“钱”匹配，则智能手机将在用户想要播放该语音信息时，通过听筒播放该语音信息。除此之外，当语音信息的声纹特征和李四的声纹模版不匹配时，或者，当语音信息的语音文本和文本模版不匹配时，智能手机都将使用扬声器播放该语音信息。For another example, still taking the terminal as an example of a smart phone, the flow of the method shown in FIG. 3C will be described. Wherein, the first playing component is an earpiece, and the second playing component is a loudspeaker. In FIG. 3C , when the voiceprint features in the voice information conform to the voiceprint template, and the voice text in the voice information matches the text template, the smart phone uses the first playback component to play the voice information. When any one of the above two conditions is not met, use the second playing component to play the voice information. The smart phone first sets information through the user's relationship, and establishes a corresponding relationship between the text template and the first playback component, such as establishing a corresponding relationship between the text template "money" and the receiver. At the same time, the voiceprint template to be used is downloaded from the server, such as Li Si's voiceprint template. When the voiceprint feature detected by the smartphone matches the voiceprint template of Li Si from the local recording or received information, and the detected voice text matches the text template "Qian", the smartphone will When you want to play the voice message, play the voice message through the earpiece. In addition, when the voiceprint feature of the voice message does not match the voiceprint template of Li Si, or when the voice text of the voice message does not match the text template, the smart phone will use the speaker to play the voice message.
综上所述，本发明实施例公开的语音信息的播放方法，通过获取语音信息，分析语音信息，获取该语音信息的信息特征，判断信息特征与特征模版是否匹配，当信息特征与特征模版匹配时，确定对语音信息进行播放的播放组件为第一播放组件，当信息特征与特征模版不匹配时，确定对语音信息进行播放的播放组件为第二播放组件，根据确定的播放组件播放语音信息；解决了相关技术中用户每次想要通过非默认播放组件播放语音信息时，都需要通过手动操作的方式选择通过非默认播放组件进行播放的选项的问题；由于本发明实施例能够在语音信息中的信息特征匹配时使用第一播放组件播放该语音信息，在不匹配时使用第二播放组件播放该语音信息。因此，本发明实施例能够免去用户在播放语音信息前手动选择播放方式的步骤，在保证语音信息以正确的播放组件播放的前提下，简化用户的操作，提高了语音信息的播放效率。To sum up, the method for playing voice information disclosed in the embodiment of the present invention acquires the voice information, analyzes the voice information, obtains the information features of the voice information, and judges whether the information features match the feature template. When the information feature matches the feature template , it is determined that the playback component that plays the voice information is the first playback component, and when the information feature does not match the feature template, it is determined that the playback component that plays the voice information is the second playback component, and the voice information is played according to the determined playback component ; Solve the problem that in the related art, when the user wants to play voice information through a non-default playback component every time, he needs to manually select the option to play through a non-default playback component; When the characteristics of the information match, use the first playback component to play the voice information, and use the second playback component to play the voice information when they do not match. Therefore, the embodiment of the present invention can save the user from the step of manually selecting the playback mode before playing the voice information, simplifies the user's operation and improves the playback efficiency of the voice information on the premise of ensuring that the voice information is played by the correct playback component.
另外，由于本发明实施例能够对语音信息进行语音识别，在获取的语音信息对应的语音文本与文本模版匹配时，使用第一播放组件播放语音信息，在获取的语音信息对应的语音模版和文本模版不匹配时，使用第二播放组件播放语音信息。因此，本发明实施例还达到了根据语音信息中的文本自动确定合适的播放方式，令使用者在无需手动选择语音信息的播放方式的前提下，能够通过合适的播放组件收听到语音信息。In addition, since the embodiment of the present invention can perform voice recognition on voice information, when the voice text corresponding to the acquired voice information matches the text template, the first playback component is used to play the voice information, and the voice template and text corresponding to the acquired voice information When the templates do not match, use the second playback component to play the voice information. Therefore, the embodiment of the present invention also automatically determines the appropriate playback mode according to the text in the voice information, so that the user can listen to the voice information through a suitable playback component without manually selecting the playback mode of the voice information.
另外，由于本发明实施例能够对语音信息进行声纹识别，在获取的语音信息的声纹特征与声纹模版匹配时，使用第一播放组件播放语音信息，在获取的语音信息的声纹特征和文本模版不匹配时，使用第二播放组件播放语音信息。因此，本发明实施例还达到了根据语音信息的声纹自动确定合适的播放方式的效果，提高了在播放语音时选择播放组件的智能程度。In addition, since the embodiment of the present invention can perform voiceprint recognition on voice information, when the voiceprint feature of the acquired voice information matches the voiceprint template, the first playback component is used to play the voice information, and the voiceprint feature of the acquired voice information When it does not match the text template, use the second playback component to play the voice information. Therefore, the embodiment of the present invention also achieves the effect of automatically determining a suitable playback mode according to the voiceprint of the voice information, and improves the intelligence of selecting playback components when playing voice.
另外，由于本发明实施例能够接收关系建立指令，根据该关系建立指令建立特征模版和播放组件之间的对应关系。因此，本发明实施例能够提供给用户一种建立特征模版和播放组件之间关系的功能，提高了确定语音信息的特征模版对应的播放组件的便捷性。In addition, since the embodiment of the present invention can receive a relationship establishment instruction, the corresponding relationship between the feature template and the playback component is established according to the relationship establishment instruction. Therefore, the embodiments of the present invention can provide users with a function of establishing a relationship between feature templates and playback components, which improves the convenience of determining the playback components corresponding to feature templates of voice information.
另外，在根据确定的播放组件播放语音信息前，本发明实施例能够展示提示信息，该提示信息用于为用户指明当前播放语音信息所使用的播放组件，该方式避免了用户在不知晓播放组件时，听不到该语音信息。例如在播放组件是听筒时，用户在没有提示信息时可能不会将听筒靠近耳边，而导致听不到该语音信息。因此，本发明实施例基于该特征能够保证用户听到该语音信息，提高语音信息中的信息在表达时的可靠性。In addition, before the audio information is played according to the determined playback component, the embodiment of the present invention can display prompt information, which is used to indicate to the user the playback component currently used to play the voice information. , the voice message cannot be heard. For example, when the playback component is an earpiece, the user may not put the earpiece close to the ear when there is no prompt information, so that the voice information cannot be heard. Therefore, the embodiment of the present invention can ensure that the user hears the voice information based on this feature, and improve the reliability of the information in the voice information when expressed.
在本发明实施例中，当终端对应三种或三种以上的播放组件时，可以通过图4所示的方法来播放语音信息，详述如下。In the embodiment of the present invention, when the terminal corresponds to three or more playing components, the voice information can be played through the method shown in FIG. 4 , which is described in detail as follows.
请参见图4，其是本发明一个实施例提供的另一种语音信息的播放方法的流程图，该语音信息的播放方法可以包括：Please refer to FIG. 4 , which is a flow chart of another method for playing voice information provided by an embodiment of the present invention. The method for playing voice information may include:
步骤401，接收关系建立指令，关系建立指令用于指示建立特征模版和播放组件之间的对应关系。Step 401, receiving a relationship establishment instruction, which is used to instruct the establishment of a corresponding relationship between a feature template and a playback component.
步骤402，根据关系建立指令建立特征模版和播放组件之间的对应关系。Step 402, establish the corresponding relationship between the feature template and the playback component according to the relationship establishing instruction.
其中，步骤401的执行方式和步骤201的执行方式相同，步骤402的执行方式和步骤202的执行方式相同，有关步骤401和步骤402执行的过程可参见步骤201和步骤202的执行过程，此处不再赘述。Wherein, the execution method of step 401 is the same as the execution method of step 201, the execution method of step 402 is the same as the execution method of step 202, and the execution process of step 401 and step 402 can refer to the execution process of step 201 and step 202, here No longer.
步骤403，获取语音信息，该语音信息是以声音片段的形式进行播放的信息。In step 403, voice information is acquired, and the voice information is played in the form of sound clips.
其中，步骤403的执行方式和步骤101的执行方式相同，有关步骤403执行的过程可参见步骤101的执行过程，此处不再展开论述。Wherein, the execution method of step 403 is the same as the execution method of step 101, and the execution process of step 403 may refer to the execution process of step 101, which will not be further discussed here.
步骤404，分析语音信息，获取该语音信息的信息特征。Step 404, analyzing the voice information to obtain information features of the voice information.
其中，步骤404的执行方式和步骤204的执行方式相同，详情请参见步骤204的执行过程，此处不再展开论述。Wherein, the execution method of step 404 is the same as the execution method of step 204, please refer to the execution process of step 204 for details, and will not be further discussed here.
步骤405，判断信息特征与特征模版是否匹配。Step 405, judging whether the information feature matches the feature template.
在本发明实施例中，特征模版是预设的至少两个特征模版中的一个，且每个特征模版对应一种播放组件。比如，图4所示的语音信息的播放方法中，终端对应三种或者三种以上的播放组件，每一个特征模版都对应有一个播放组件。在此情况下，为了准确确定用于播放语音信息的播放组件，需要判断语音信息中的信息特征与特征模版是否匹配，并在匹配时确定匹配的特征模版，以便确定该特征模版对应的播放组件。In the embodiment of the present invention, the feature template is one of at least two preset feature templates, and each feature template corresponds to a playback component. For example, in the voice information playing method shown in FIG. 4 , the terminal corresponds to three or more playing components, and each characteristic template corresponds to a playing component. In this case, in order to accurately determine the playback component used to play the voice information, it is necessary to judge whether the information feature in the voice information matches the feature template, and determine the matching feature template when matching, so as to determine the playback component corresponding to the feature template .
可选地，特征模版包括文本模版和声纹模版。Optionally, the feature template includes a text template and a voiceprint template.
步骤406，在信息特征与特征模版匹配时，确定该特征模版对应的播放组件为播放语音信息的播放组件。Step 406, when the information feature matches the feature template, determine that the player component corresponding to the feature template is the player component for playing the voice information.
步骤407，在信息特征与特征模版不匹配时，确定预设的通用播放组件为播放语音信息的播放组件。Step 407, when the information feature does not match the feature template, determine that the preset general playback component is the playback component for playing the voice information.
为了使本发明实施例中的步骤405至步骤407记载的方案的执行步骤更易理解，下面通过表三和表四来示意性说明一种确定播放组件的过程。In order to make the execution steps of the solution recorded in steps 405 to 407 in the embodiment of the present invention easier to understand, the following uses Table 3 and Table 4 to schematically illustrate a process of determining a playback component.
表三Table three
表四Table four
在本发明实施例中，终端在执行步骤303前，已获取如表三中所示语音信息中的信息特征。其中，每一条语音信息都对应有该语音信息的信息特征。当终端获取到其中一条语音信息的信息特征时，智能手机将该信息特征和表四中除序号为4的一行外的特征模版进行比对。当该信息特征与表四中的特征模版相匹配时，终端将该特征模版对应的播放组件确定为播放语音信息的播放组件。例如，终端收到的语音信息是“语音信息2”，在终端通过语音分析获得该语音信息中包含的信息特征是“王五声纹”后，终端将该“王五声纹”与表四中所示的特征模版进行比对，结果检测到该“王五声纹”和序号为2的特征模版匹配，该特征模版对应的播放组件是听筒。随后，终端在检测到用户指示播放该语音信息的操作时，通过听筒播放该“语音信息2”。In the embodiment of the present invention, before the terminal executes step 303, the information features in the voice information shown in Table 3 have been obtained. Wherein, each piece of voice information corresponds to the information feature of the voice information. When the terminal obtains the information feature of one of the voice messages, the smart phone compares the information feature with the feature templates in Table 4 except for the line with the serial number 4. When the information feature matches the feature template in Table 4, the terminal determines the playback component corresponding to the feature template as the playback component for playing the voice information. For example, the voice information received by the terminal is "Voice Information 2". After the terminal obtains through voice analysis that the information feature contained in the voice information is "Wang Wushengprint", the terminal combines the "Wang Wushengprint" with the information shown in Table 4. The characteristic template was compared, and it was detected that the "Wang Wushengprint" matched the characteristic template with the serial number 2, and the playback component corresponding to the characteristic template was the earpiece. Subsequently, when the terminal detects the user's instruction to play the voice information, it plays the "voice information 2" through the earpiece.
在表四中，需要特别说明的是，序号为4的一行特征模版用于表示，当语音信息的信息特征和特征模版都不匹配时，通过通用播放组件“扬声器”播放该语音信息。In Table 4, it should be noted that a row of feature templates numbered 4 is used to indicate that when the information features of the voice information and the feature templates do not match, the voice information will be played through the general playback component "speaker".
步骤408，对应语音信息展示提示信息，该提示信息用于指示播放语音信息所使用的播放组件。Step 408, display prompt information corresponding to the voice information, and the prompt information is used to indicate the playback component used to play the voice information.
步骤408的执行方式与步骤208的执行方式相同，步骤408的执行详情可参见步骤208的执行方式，此处不再赘述。The execution method of step 408 is the same as the execution method of step 208. For details of the execution of step 408, please refer to the execution method of step 208, which will not be repeated here.
步骤409，根据确定的播放组件播放语音信息。Step 409, play the voice information according to the determined playing component.
步骤409的执行方式与步骤104的执行方式相同，步骤409的执行详情可参见步骤104的执行方式，此处不再赘述。The execution method of step 409 is the same as the execution method of step 104. For details of the execution of step 409, please refer to the execution method of step 104, which will not be repeated here.
比如，以终端是智能手机为例，对图4所示的方法流程进行说明。其中，智能手机控制三个播放组件，第一个播放组件是听筒，第二个播放组件是扬声器，第三个播放组件是蓝牙音箱。智能手机在接收语音信息之前，可以先从服务器中下载要使用的声纹模版，如赵六的声纹模版。以及，在智能手机中接收根据用户的操作产生的关系建立指令，建立各个文本模版和播放组件之间的对应关系。例如，用户设置的特征模版是文本模版“账户/帐户”，该特征模版对应的播放组件是听筒。用户设置的特征模版是文本模版“公告”和声纹模版“赵六的声纹模版”，该声纹模版对应的播放组件是蓝牙音箱。在上述设置完成后，终端接收语音信息，分析语音信息的信息特征，当该信息特征与文本模版“账户/帐户”匹配时，该终端确定听筒为播放该语音信息的播放组件。当该信息特征的声纹特征和赵六的声纹模版匹配时，且该信息特征中包含文本模版“公告”，则终端确定蓝牙音箱为播放该语音信息的播放组件。此外，当语音信息的信息特征和特征模版不匹配，均通过预设的通用播放组件扬声器来播放该语音信息。For example, taking the terminal being a smart phone as an example, the flow of the method shown in FIG. 4 will be described. Among them, the smart phone controls three playback components, the first playback component is an earpiece, the second playback component is a speaker, and the third playback component is a Bluetooth speaker. Before receiving voice information, the smart phone can download the voiceprint template to be used from the server, such as Zhao Liu's voiceprint template. And, receiving the relationship establishing instruction generated according to the operation of the user in the smart phone, and establishing the corresponding relationship between each text template and the playing component. For example, the feature template set by the user is a text template "account/account", and the playback component corresponding to this feature template is an earpiece. The feature templates set by the user are the text template "announcement" and the voiceprint template "Zhao Liu's voiceprint template". The playback component corresponding to the voiceprint template is a Bluetooth speaker. After the above settings are completed, the terminal receives the voice information, analyzes the information characteristics of the voice information, and when the information characteristics match the text template "account/account", the terminal determines that the earpiece is the playback component for playing the voice information. When the voiceprint feature of the information feature matches Zhao Liu's voiceprint template, and the information feature contains the text template "announcement", the terminal determines that the Bluetooth speaker is the playback component for playing the voice information. In addition, when the information feature of the voice information does not match the feature template, the voice information is played through the preset universal playback component speaker.
综上所述，本发明实施例公开的语音信息的播放方法，通过获取语音信息，分析语音信息，获取该语音信息的信息特征，判断信息特征与特征模版是否匹配，在信息特征与特征模版匹配时，确定该特征模版对应的播放组件为播放语音信息的播放组件；在信息特征与特征模版不匹配时，确定预设的通用播放组件为播放语音信息的播放组件，根据确定的播放组件播放语音信息；解决了相关技术中用户每次想要通过非默认播放组件播放语音信息时，都需要通过手动操作的方式选择通过非默认播放组件进行播放的选项的问题；由于本发明实施例能够在语音信息中的信息特征与特征模版匹配时，使用该匹配的特征模版对应的播放组件播放语音信息，在信息特征与和特征模版不匹配时，使用通用播放组件播放该语音信息。因此，本发明实施例能够在终端控制多个播放组件时，令与特征模版匹配的语音信息直接通过对应的播放组件播放，简化用户的操作，提高了终端自动选择播放语音信息的设备的能力。In summary, the method for playing voice information disclosed in the embodiments of the present invention obtains the voice information, analyzes the voice information, obtains the information features of the voice information, and judges whether the information features match the feature template. , it is determined that the playback component corresponding to the feature template is the playback component for playing voice information; when the information feature does not match the feature template, it is determined that the preset general playback component is the playback component for playing voice information, and the voice is played according to the determined playback component information; solve the problem that in the related art, when a user wants to play voice information through a non-default playback component every time, he needs to manually select the option to play through a non-default playback component; When the information feature in the information matches the feature template, use the playback component corresponding to the matched feature template to play the voice information, and when the information feature does not match the feature template, use the general playback component to play the voice information. Therefore, in the embodiment of the present invention, when the terminal controls multiple playback components, the voice information matching the feature template can be played directly through the corresponding playback components, which simplifies the user's operation and improves the terminal's ability to automatically select the device for playing voice information.
另外，由于本发明实施例能够接收关系建立指令，根据该关系建立指令建立特征模版和播放组件之间的对应关系。因此，本发明实施例能够提供给用户一种建立特征模版和播放组件之间关系的功能，提高了确定语音信息的特征模版对应的播放组件的便捷性。In addition, since the embodiment of the present invention can receive a relationship establishment instruction, the corresponding relationship between the feature template and the playback component is established according to the relationship establishment instruction. Therefore, the embodiments of the present invention can provide users with a function of establishing a relationship between feature templates and playback components, which improves the convenience of determining the playback components corresponding to feature templates of voice information.
另外，在根据确定的播放组件播放语音信息前，本发明实施例能够展示提示信息，该提示信息用于为用户指明当前播放语音信息所使用的播放组件，该方式避免了用户在不知晓播放组件时，听不到该语音信息。例如在播放组件是听筒时，用户在没有提示信息时可能不会将听筒靠近耳边，而导致听不到该语音信息。因此，本发明实施例基于该特征能够保证用户听到该语音信息，提高语音信息中的信息在表达时的可靠性。In addition, before the audio information is played according to the determined playback component, the embodiment of the present invention can display prompt information, which is used to indicate to the user the playback component currently used to play the voice information. , the voice message cannot be heard. For example, when the playback component is an earpiece, the user may not put the earpiece close to the ear when there is no prompt information, so that the voice information cannot be heard. Therefore, the embodiment of the present invention can ensure that the user hears the voice information based on this feature, and improve the reliability of the information in the voice information when expressed.
下述为本发明装置实施例，可以用于执行本发明方法实施例。对于本发明装置实施例中未披露的细节，请参照本发明方法实施例。The following are device embodiments of the present invention, which can be used to implement the method embodiments of the present invention. For the details not disclosed in the device embodiment of the present invention, please refer to the method embodiment of the present invention.
请参考图5，其是本发明一个实施例提供的一种语音信息的播放装置的结构方框图，该语音信息的播放装置可通过软件、硬件或者两者的结合实现成为终端的部分或者全部。该语音信息的播放装置可以包括：获取模块510、分析模块520、确定模块530和播放模块540。Please refer to FIG. 5 , which is a structural block diagram of a device for playing voice information provided by an embodiment of the present invention. The device for playing voice information can be implemented as part or all of a terminal through software, hardware or a combination of the two. The apparatus for playing the voice information may include: an acquisition module 510 , an analysis module 520 , a determination module 530 and a playback module 540 .
获取模块510，用于获取语音信息，语音信息是以声音片段的形式进行播放的信息。The acquiring module 510 is configured to acquire voice information, and the voice information is information played in the form of sound clips.
分析模块520，用于分析语音信息，获取语音信息的信息特征。The analysis module 520 is configured to analyze the voice information, and obtain information features of the voice information.
确定模块530，用于根据语音信息的信息特征确定对语音信息进行播放的播放组件。The determining module 530 is configured to determine a playback component for playing the voice information according to information characteristics of the voice information.
播放模块540，用于根据确定的播放组件播放语音信息。The playing module 540 is configured to play the voice information according to the determined playing component.
综上所述，本发明实施例提供的语音信息的播放装置，通过获取语音信息，该语音信息是以声音片段的形式进行播放的信息；分析语音信息，获取该语音信息的信息特征；根据语音信息的信息特征确定对语音信息进行播放的播放组件；根据确定的播放组件播放语音信息；解决了移动终端在不同的使用场景中，需要用户选择语音信息的播放方式造成的操作繁琐的问题；由于本发明实施例在播放语音信息前，获取了语音信息的信息特征，根据语音信息的信息特征确定了播放组件后，直接通过该播放组件播放语音信息。因此，在播放语音信息时，该播放方法无需用户手动去选择播放组件，能够直接使用语音信息的信息特征对应的播放组件播放语音信息；省去了用户在播放语音信息前的指定播放组件的步骤，提高了移动终端在不同使用场景中播放语音信息的效率。To sum up, the device for playing voice information provided by the embodiments of the present invention obtains voice information, which is played in the form of sound clips; analyzes the voice information to obtain information features of the voice information; The information characteristics of the information determine the playback component for playing the voice information; play the voice information according to the determined playback component; solve the problem of cumbersome operation caused by the need for the user to select the playback mode of the voice information in different usage scenarios of the mobile terminal; due to In the embodiment of the present invention, before playing the voice information, the information features of the voice information are acquired, and after the playback component is determined according to the information features of the voice information, the voice information is played directly through the playback component. Therefore, when playing the voice information, the playback method does not require the user to manually select the playback component, and can directly use the playback component corresponding to the information feature of the voice information to play the voice information; the step of specifying the playback component before the user plays the voice information is omitted , improving the efficiency of the mobile terminal in playing voice information in different usage scenarios.
请参考图6，其是本发明一个实施例提供的另一种语音信息的播放装置的结构方框图，该语音信息的播放装置可通过软件、硬件或者两者的结合实现成为终端的部分或者全部。该语音信息的播放装置可以包括：获取模块610、分析模块620、确定模块630和播放模块640。Please refer to FIG. 6 , which is a structural block diagram of another voice information playback device provided by an embodiment of the present invention. The voice information playback device can be implemented as part or all of a terminal through software, hardware or a combination of the two. The device for playing the voice information may include: an acquisition module 610 , an analysis module 620 , a determination module 630 and a playback module 640 .
获取模块610，用于获取语音信息，语音信息是以声音片段的形式进行播放的信息。The acquiring module 610 is configured to acquire voice information, and the voice information is information played in the form of sound clips.
分析模块620，用于分析语音信息，获取语音信息的信息特征。The analysis module 620 is configured to analyze the voice information, and acquire information features of the voice information.
确定模块630，用于根据语音信息的信息特征确定对语音信息进行播放的播放组件。The determining module 630 is configured to determine a playback component for playing the voice information according to information characteristics of the voice information.
播放模块640，用于根据确定的播放组件播放语音信息。The playing module 640 is configured to play the voice information according to the determined playing component.
可选地，确定模块630，包括：判断单元631、第一确定单元632和第二确定单元633。Optionally, the determining module 630 includes: a judging unit 631 , a first determining unit 632 and a second determining unit 633 .
判断单元631，用于判断信息特征与特征模版是否匹配。Judging unit 631, configured to judge whether the information feature matches the feature template.
第一确定单元632，用于当信息特征与特征模版匹配时，确定对语音信息进行播放的播放组件为第一播放组件。The first determining unit 632 is configured to determine that the playback component that plays the voice information is the first playback component when the information feature matches the feature template.
第二确定单元633，用于当信息特征与特征模版不匹配时，确定对语音信息进行播放的播放组件为第二播放组件。The second determining unit 633 is configured to determine that the playing component that plays the voice information is the second playing component when the information feature does not match the feature template.
可选地，分析模块620，包括：语音识别单元621。判断单元631，包括：语音判断子单元631a。Optionally, the analysis module 620 includes: a speech recognition unit 621 . The judging unit 631 includes: a speech judging subunit 631a.
语音识别单元621，用于对语音信息进行语音识别，获得语音信息对应的语音文本。The voice recognition unit 621 is configured to perform voice recognition on the voice information, and obtain voice text corresponding to the voice information.
语音判断子单元631a，用于判断语音文本和文本模版是否匹配。The speech judging subunit 631a is used to judge whether the speech text matches the text template.
可选地，分析模块620，包括：声纹识别单元622。判断单元631，包括：声纹判断子单元631b。Optionally, the analysis module 620 includes: a voiceprint recognition unit 622 . The judging unit 631 includes: a voiceprint judging subunit 631b.
声纹识别单元622，用于对语音信息进行声纹识别，获得语音信息的声纹特征。The voiceprint recognition unit 622 is configured to perform voiceprint recognition on the voice information to obtain voiceprint characteristics of the voice information.
声纹判断子单元631b，用于判断声纹特征和声纹模版是否匹配。The voiceprint judging subunit 631b is used to judge whether the voiceprint feature matches the voiceprint template.
可选地，在本发明实施例所示的装置的一种可能实现的方式中，确定模块630还包括：第三确定单元634。Optionally, in a possible implementation manner of the apparatus shown in the embodiment of the present invention, the determining module 630 further includes: a third determining unit 634 .
判断单元631，用于判断信息特征与特征模版是否匹配。Judging unit 631, configured to judge whether the information feature matches the feature template.
第三判断单元634，用于当信息特征与所述特征模版匹配时，确定对语音信息进行播放的播放组件为特征模版对应的播放组件。The third judging unit 634 is configured to determine that the playback component that plays the voice information is the playback component corresponding to the feature template when the information feature matches the feature template.
可选地，在本发明实施例所示的装置的另一种可能实现的方式中，该装置还包括：接收模块650和设置模块660。Optionally, in another possible implementation manner of the device shown in the embodiment of the present invention, the device further includes: a receiving module 650 and a setting module 660 .
接收模块650，用于接收关系建立指令，关系建立指令用于指示建立特征模版和播放组件之间的对应关系。The receiving module 650 is configured to receive a relationship establishment instruction, and the relationship establishment instruction is used to instruct to establish a corresponding relationship between a feature template and a playback component.
设置模块660，用于根据关系建立指令建立特征模版和播放组件之间的对应关系。The setting module 660 is configured to establish the corresponding relationship between the characteristic template and the playing component according to the relationship establishing instruction.
可选地，在本发明实施例所示的装置的另一种可能实现的方式中，该装置还包括：展示模块670。Optionally, in another possible implementation manner of the device shown in the embodiment of the present invention, the device further includes: a display module 670 .
展示模块670，用于对应语音信息展示提示信息，提示信息用于指示播放语音信息所使用的播放组件。The display module 670 is configured to display prompt information corresponding to the voice information, and the prompt information is used to indicate the playback component used to play the voice information.
相关细节参见上述方法实施例。For relevant details, refer to the above method embodiments.
图7示出了本发明一个示例性实施例所涉及的终端的结构示意图。该终端包括：该终端包括：处理器711、接收器712、发射器713、存储器714和总线715。Fig. 7 shows a schematic structural diagram of a terminal involved in an exemplary embodiment of the present invention. The terminal includes: the terminal includes: a processor 711 , a receiver 712 , a transmitter 713 , a memory 714 and a bus 715 .
处理器711包括一个或者一个以上处理核心，存储器714通过总线715与处理器711相连，存储器714用于存储程序指令，处理器711执行存储器714中的程序指令时实现上述方法实施例中语音信息的播放方法。The processor 711 includes one or more processing cores, and the memory 714 is connected to the processor 711 through the bus 715. The memory 714 is used to store program instructions. Play method.
接收器712和发射器713可以实现为一个通信组件，该通信组件可以是一块通信芯片，用于对信息进行调制和/或解调，并通过无线信号接收或发送该信息。The receiver 712 and the transmitter 713 can be implemented as a communication component, which can be a communication chip, and is used for modulating and/or demodulating information, and receiving or sending the information through wireless signals.
此外，存储器714可以由任何类型的易失性或非易失性存储设备或者它们的组合实现，如静态随时存取存储器(SRAM)，电可擦除可编程只读存储器(EEPROM)，可擦除可编程只读存储器(EPROM)，可编程只读存储器(PROM)，只读存储器(ROM)，磁存储器，快闪存储器，磁盘或光盘。In addition, the memory 714 can be implemented by any type of volatile or non-volatile memory device or their combination, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable In addition to programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk.
上述结构示意仅为对终端的示意性说明，终端可以包括更多或更少的部件，比如终端可以不包括发送器，或者，终端还包括传感器、显示屏、电源等其它部件，本实施例不再赘述。The above structural illustration is only a schematic illustration of the terminal, and the terminal may include more or fewer components. For example, the terminal may not include a transmitter, or the terminal may also include other components such as a sensor, a display screen, and a power supply. This embodiment does not Let me repeat.
本发明实施例还提供一种计算机可读介质，其上存储有程序指令，程序指令被处理器711执行时实现上述方法实施例中的语音信息的播放方法。The embodiment of the present invention also provides a computer-readable medium on which program instructions are stored. When the program instructions are executed by the processor 711, the method for playing voice information in the above method embodiments is implemented.
上述本申请实施例序号仅仅为了描述，不代表实施例的优劣。The serial numbers of the above embodiments of the present application are for description only, and do not represent the advantages and disadvantages of the embodiments.
本领域普通技术人员可以理解实现上述实施例的全部或部分步骤可以通过硬件来完成，也可以通过程序来指令相关的硬件完成，所述的程序可以存储于一种计算机可读存储介质中，上述提到的存储介质可以是只读存储器，磁盘或光盘等。Those of ordinary skill in the art can understand that all or part of the steps for implementing the above embodiments can be completed by hardware, and can also be completed by instructing related hardware through a program. The program can be stored in a computer-readable storage medium. The above-mentioned The storage medium mentioned may be a read-only memory, a magnetic disk or an optical disk, and the like.
以上所述仅为本申请的较佳实施例，并不用以限制本申请，凡在本申请的精神和原则之内，所作的任何修改、等同替换、改进等，均应包含在本申请的保护范围之内。The above descriptions are only preferred embodiments of the application, and are not intended to limit the application. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of the application shall be included in the protection of the application. within range.
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710611657.5ACN107205095A (en) | 2017-07-25 | 2017-07-25 | Voice information playback method, device and terminal |
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710611657.5ACN107205095A (en) | 2017-07-25 | 2017-07-25 | Voice information playback method, device and terminal |
| Publication Number | Publication Date |
|---|---|
| CN107205095Atrue CN107205095A (en) | 2017-09-26 |
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710611657.5APendingCN107205095A (en) | 2017-07-25 | 2017-07-25 | Voice information playback method, device and terminal |
| Country | Link |
|---|---|
| CN (1) | CN107205095A (en) |
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109213468A (en)* | 2018-08-23 | 2019-01-15 | 阿里巴巴集团控股有限公司 | A kind of speech playing method and device |
| CN110012164A (en)* | 2019-03-29 | 2019-07-12 | 努比亚技术有限公司 | A kind of sound playing method of equipment, wearable device and computer readable storage medium |
| CN110502300A (en)* | 2019-08-14 | 2019-11-26 | 上海掌门科技有限公司 | Speech playing method, equipment and computer-readable medium |
| CN114566163A (en)* | 2022-02-23 | 2022-05-31 | 成都智元汇信息技术股份有限公司 | Public traffic voice processing method, device, system, electronic equipment and medium |
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7155729B1 (en)* | 2000-03-28 | 2006-12-26 | Microsoft Corporation | Method and system for displaying transient notifications |
| CN102572839A (en)* | 2010-12-14 | 2012-07-11 | 中国移动通信集团四川有限公司 | Method and system for controlling voice communication |
| CN105721913A (en)* | 2015-12-18 | 2016-06-29 | 中科创达软件科技（深圳）有限公司 | Multimedia file resume method and apparatus |
| CN106095383A (en)* | 2016-06-16 | 2016-11-09 | 捷开通讯(深圳)有限公司 | A kind of mobile terminal and acoustic pattern method to set up thereof |
| CN106302997A (en)* | 2016-07-29 | 2017-01-04 | 联想(北京)有限公司 | A kind of output control method, electronic equipment and system |
| CN106888327A (en)* | 2017-02-28 | 2017-06-23 | 北京小米移动软件有限公司 | Speech playing method and device |
| CN106973168A (en)* | 2017-05-04 | 2017-07-21 | 广东欧珀移动通信有限公司 | Voice playing method and device and computer equipment |
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7155729B1 (en)* | 2000-03-28 | 2006-12-26 | Microsoft Corporation | Method and system for displaying transient notifications |
| CN102572839A (en)* | 2010-12-14 | 2012-07-11 | 中国移动通信集团四川有限公司 | Method and system for controlling voice communication |
| CN105721913A (en)* | 2015-12-18 | 2016-06-29 | 中科创达软件科技（深圳）有限公司 | Multimedia file resume method and apparatus |
| CN106095383A (en)* | 2016-06-16 | 2016-11-09 | 捷开通讯(深圳)有限公司 | A kind of mobile terminal and acoustic pattern method to set up thereof |
| CN106302997A (en)* | 2016-07-29 | 2017-01-04 | 联想(北京)有限公司 | A kind of output control method, electronic equipment and system |
| CN106888327A (en)* | 2017-02-28 | 2017-06-23 | 北京小米移动软件有限公司 | Speech playing method and device |
| CN106973168A (en)* | 2017-05-04 | 2017-07-21 | 广东欧珀移动通信有限公司 | Voice playing method and device and computer equipment |
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109213468A (en)* | 2018-08-23 | 2019-01-15 | 阿里巴巴集团控股有限公司 | A kind of speech playing method and device |
| CN110012164A (en)* | 2019-03-29 | 2019-07-12 | 努比亚技术有限公司 | A kind of sound playing method of equipment, wearable device and computer readable storage medium |
| CN110502300A (en)* | 2019-08-14 | 2019-11-26 | 上海掌门科技有限公司 | Speech playing method, equipment and computer-readable medium |
| CN114566163A (en)* | 2022-02-23 | 2022-05-31 | 成都智元汇信息技术股份有限公司 | Public traffic voice processing method, device, system, electronic equipment and medium |
| CN114566163B (en)* | 2022-02-23 | 2023-05-02 | 成都智元汇信息技术股份有限公司 | Public transport voice processing method, device, system, electronic equipment and medium |
| Publication | Publication Date | Title |
|---|---|---|
| CN107580113B (en) | Prompting method, prompting device, storage medium and terminal | |
| KR101633208B1 (en) | Instant communication voice recognition method and terminal | |
| CN106354471A (en) | Method and device for audio play control and electronic device | |
| US20110066438A1 (en) | Contextual voiceover | |
| US9277320B1 (en) | Managing and using headset profiles for different headsets | |
| WO2016184119A1 (en) | Volume adjustment method, system and equipment, and computer storage medium | |
| CN107562405B (en) | Audio playback control method, device, storage medium and mobile terminal | |
| CN108391205A (en) | Left and right acoustic channels switching method and apparatus, readable storage medium storing program for executing, terminal | |
| CN105632508A (en) | Audio frequency processing method and audio frequency processing device | |
| CN108538320A (en) | Recording control method and device, readable storage medium storing program for executing, terminal | |
| CN108803859A (en) | Information processing method, device, terminal, earphone and readable storage medium | |
| CN106126172B (en) | A sound effect processing method and mobile terminal | |
| KR20140074549A (en) | Method and apparatus for providing context aware service using speech recognition | |
| CN108922537A (en) | Audio recognition method, device, terminal, earphone and readable storage medium | |
| CN111083289B (en) | Audio playing method and device, storage medium and mobile terminal | |
| CN106652996A (en) | Prompt tone generating method and device and mobile terminal | |
| WO2017181365A1 (en) | Earphone channel control method, related apparatus, and system | |
| WO2017166603A1 (en) | Sound quality adjustment method, terminal, electronic device, and non-volatile computer storage medium | |
| JP6449991B2 (en) | Media file processing method and terminal | |
| CN107205095A (en) | Voice information playback method, device and terminal | |
| JP2019505944A (en) | Audio file re-recording method, apparatus and storage medium | |
| CN107342082A (en) | Audio-frequency processing method, device and audio-frequence player device based on interactive voice | |
| CN107371102A (en) | Audio playback volume control method, device, storage medium and mobile terminal | |
| CN107316637A (en) | Speech recognition method and related products | |
| CN106297839A (en) | A kind of audio-frequence player 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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication | Application publication date:20170926 |