WO2014026605A1 - 一种语音识别系统和方法 - Google Patents

一种语音识别系统和方法 Download PDF

Info

Publication number
WO2014026605A1
WO2014026605A1 PCT/CN2013/081432 CN2013081432W WO2014026605A1 WO 2014026605 A1 WO2014026605 A1 WO 2014026605A1 CN 2013081432 W CN2013081432 W CN 2013081432W WO 2014026605 A1 WO2014026605 A1 WO 2014026605A1
Authority
WO
WIPO (PCT)
Prior art keywords
audio signal
digital audio
bluetooth
signal
main control
Prior art date
Application number
PCT/CN2013/081432
Other languages
English (en)
French (fr)
Inventor
王平平
郄勇
Original Assignee
歌尔声学股份有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 歌尔声学股份有限公司 filed Critical 歌尔声学股份有限公司
Priority to US14/415,813 priority Critical patent/US20150213797A1/en
Priority to KR1020157002167A priority patent/KR20150032731A/ko
Publication of WO2014026605A1 publication Critical patent/WO2014026605A1/zh

Links

Images

Classifications

    • G—PHYSICS
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
    • G10L17/00—Speaker identification or verification
    • G—PHYSICS
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
    • G10L15/00—Speech recognition
    • G10L15/28—Constructional details of speech recognition systems
    • G10L15/30—Distributed recognition, e.g. in client-server systems, for mobile phones or network applications
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04R—LOUDSPEAKERS, MICROPHONES, GRAMOPHONE PICK-UPS OR LIKE ACOUSTIC ELECTROMECHANICAL TRANSDUCERS; DEAF-AID SETS; PUBLIC ADDRESS SYSTEMS
    • H04R3/00—Circuits for transducers, loudspeakers or microphones
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04R—LOUDSPEAKERS, MICROPHONES, GRAMOPHONE PICK-UPS OR LIKE ACOUSTIC ELECTROMECHANICAL TRANSDUCERS; DEAF-AID SETS; PUBLIC ADDRESS SYSTEMS
    • H04R2420/00—Details of connection covered by H04R, not provided for in its groups
    • H04R2420/07—Applications of wireless loudspeakers or wireless microphones

Definitions

  • the present invention relates to the field of speech recognition technologies, and in particular, to a speech recognition system and method.
  • the audio and video device includes: a microphone array 101, an audio encoding circuit 102, a camera 103, a video processing circuit 104, a main control integrated circuit 105, a system main control micro control unit (system master MCU) 106, and a speaker. 107 and display 108.
  • system master MCU system main control micro control unit
  • the microphone array 101 is responsible for picking up the voice signal and converting it into an analog audio signal, and then outputting it to the audio encoding circuit 102.
  • the audio encoding circuit 102 digitally encodes the analog audio signal received from the microphone array 101, and then outputs the analog audio signal to the main control integrated circuit 105.
  • the camera 103 is configured to capture a video signal and output it to the video processing circuit 104.
  • the video processing circuit 104 is configured to encode the signal output by the camera 103 and output the signal to the main control integrated circuit 105.
  • the main control integrated circuit 105 collects the video signal and audio. After the signal, the synthesized audio and video data stream is output to the system master micro control unit 106.
  • the system master micro control unit 106 is the core device of the audio and video device and is responsible for the management of the audio and video data links.
  • the audio signal output from the system master micro control unit 106 is converted into a sound signal through the audio speaker 107, and the video signal output from the system master micro control unit 106 is displayed through the display screen 108.
  • the audio and video equipment shown in FIG. 1 further includes a USB interface as a peripheral interface and a power supply circuit responsible for stable power supply of the entire system, and details are not described herein again.
  • the present invention provides a speech recognition system and method for solving the problem that a speech recognition system in which only a microphone array is used as an audio input cannot recognize distant speech.
  • the invention discloses a speech recognition system, comprising: a microphone array, an audio coding circuit, a main control integrated circuit, a Bluetooth receiving module and a Bluetooth transmitting module, wherein:
  • a microphone array for receiving a voice signal and converting it into an analog audio signal for output to an audio encoding circuit
  • An audio encoding circuit configured to convert the received analog audio signal into a digital audio signal and output the signal to the main control integrated circuit
  • a Bluetooth transmitting module configured to receive a voice signal and convert it into a digital audio signal, and then send the signal to the Bluetooth receiving module through Bluetooth;
  • a Bluetooth receiving module configured to send the received digital audio signal to the main control integrated circuit
  • the main control integrated circuit is configured to select to receive a digital audio signal from the audio encoding circuit or a digital audio signal from the Bluetooth receiving module for speech recognition processing.
  • Bluetooth receiving module there is one Bluetooth receiving module and one or more Bluetooth transmitting modules.
  • the main control integrated circuit has a button, and the main control integrated circuit selects a digital audio signal from an audio encoding circuit or a digital audio signal from a Bluetooth receiving module for voice recognition according to a user operation of the button. deal with.
  • the voice recognition system further includes: a system master micro control unit, configured to receive an audio data stream from the main control integrated circuit;
  • the system main control micro control unit has a button, and the system main control micro control unit sends an instruction for selecting a digital audio signal from the audio encoding circuit or a digital audio from the bluetooth receiving module to the main control integrated circuit according to the operation of the button by the user.
  • Signal instruction for selecting a digital audio signal from the audio encoding circuit or a digital audio from the bluetooth receiving module to the main control integrated circuit according to the operation of the button by the user.
  • the main control integrated circuit selects a digital audio signal from the audio encoding circuit or a digital audio signal from the Bluetooth receiving module to perform voice recognition processing according to an instruction of the system master micro control unit.
  • the invention also discloses a method for speech recognition, the method comprising:
  • the first digital audio signal or the second digital audio signal is selected for speech recognition processing.
  • the Bluetooth audio link includes: a Bluetooth transmitting module and a Bluetooth receiving module;
  • the receiving the voice signal through the Bluetooth audio link and converting the digital signal into the digital audio signal comprises: receiving the voice signal through the Bluetooth transmitting module and converting the signal into a digital audio signal, and transmitting the signal to the Bluetooth receiving module, where the Bluetooth receiving module takes the received digital audio signal as a
  • the second digital audio signal output is described.
  • the Bluetooth audio link includes: more than one Bluetooth transmitting module and one Bluetooth receiving module.
  • the selecting the first digital audio signal or the second digital audio signal for voice recognition processing comprises:
  • the first digital audio signal or the second digital audio signal is selected according to the user's key operation, and the selected digital audio signal is subjected to voice recognition processing.
  • the voice recognition system since the voice recognition system includes a microphone array link and a Bluetooth link two voice input links, the voice link is selected in two links, wherein the Bluetooth link is selected. Long-distance speech can be received, so long-distance speech can be identified.
  • 1 is a schematic diagram showing the composition of an existing audio and video device
  • FIG. 2 is a schematic diagram showing the composition of an audio and video device including a voice recognition system according to an embodiment of the present invention.
  • a voice signal is received through a microphone array and converted into an analog audio signal, and then the analog audio signal is converted into a digital audio signal to obtain a first digital audio signal; and the voice signal is received through a Bluetooth audio link and converted into a digital The audio signal obtains the second digital audio signal; then the first digital audio signal or the second digital audio signal is selected for speech recognition processing.
  • FIG. 2 is a schematic diagram showing the composition of an audio and video device including a voice recognition system according to an embodiment of the present invention.
  • the system includes: a microphone array 101, an audio encoding circuit 102, a camera 103, a video processing circuit 104, a main control integrated circuit 205, a system main control micro control unit 206, a speaker 107, a display screen 108, and Bluetooth receiving.
  • Module 201 and Bluetooth transmitting module 202 are illustrated in FIG. Further, since the functions of the main control integrated circuit and the system main control micro control unit are improved in the embodiment of the present invention, different reference numerals are used from those in Fig. 1.
  • the microphone array 101 is configured to receive a voice signal and convert it into an analog audio signal and output it to the audio encoding circuit 102.
  • the audio encoding circuit 102 is configured to convert the received analog audio signal into a digital audio signal and output the signal to the main control integrated circuit 205.
  • the camera 103 is used to capture the video signal and output to the video processing circuit 104, the video processing circuit 104 is used to encode the signal output by the camera 103 and output to the main control integrated circuit 205;
  • the Bluetooth transmitting module 202 is configured to receive a voice signal and convert it into a digital audio signal and then send it to the Bluetooth receiving module 201 via Bluetooth; the Bluetooth receiving module 201 is configured to send the received digital audio signal to the main control integrated circuit 205;
  • the main control integrated circuit 205 is configured to select a digital audio signal from the audio encoding circuit 102 or a digital audio signal from the Bluetooth receiving module 201 for speech recognition processing. That is, the main control integrated circuit 205 first selects between the digital audio signal from the audio encoding circuit 102 and the digital audio signal from the Bluetooth receiving module 201, and then combines the selected digital audio signal with the digital video signal from the video processing circuit 104. The synthesized audio and video data stream is output to the system master micro control unit 206.
  • the system master micro-control unit 206 is responsible for the management of the audio and video data links.
  • the audio signal output from the system master micro-control unit 206 is converted into a sound signal through the audio speaker 107, and the video signal output from the system master micro-control unit 206 is displayed through the display screen 108.
  • the microphone array audio link includes: a microphone array 101 and an audio encoding circuit 102.
  • the microphone array 101 receives the voice signal and converts it into an analog audio signal and outputs it to the audio encoding circuit 102.
  • the audio encoding circuit 102 converts the received analog audio signal.
  • the digital audio signal is output to the main control integrated circuit 205 as a first digital audio signal.
  • the Bluetooth audio link includes: a Bluetooth transmitting module 202 and a Bluetooth receiving module 201; receiving a voice signal through the Bluetooth transmitting module 202 and converting it into a digital audio signal, and transmitting the signal to the Bluetooth receiving module 201, and the Bluetooth receiving module 201 uses the received digital audio signal as The second digital audio signal is output to the main control integrated circuit 205.
  • the master integrated circuit 205 selects between the first digital audio signal and the second digital audio signal.
  • the microphone array is retained to achieve close-range speech recognition.
  • the Bluetooth voice input method is added to realize remote voice recognition.
  • Bluetooth transmission technology supports one-to-many communication, that is, a Bluetooth receiving module and multiple Bluetooth transmitting modules can be set.
  • multiple Bluetooth transmitter modules can be equipped as needed to achieve multi-point speech recognition. Since the Bluetooth signal can transmit signals over long distances, the system can perform remote voice recognition.
  • the selection of the digital audio signal by the master integrated circuit 205 can be controlled by a button.
  • a push-button control terminal may be disposed on the main control integrated circuit 205, and the main control integrated circuit 205 selects a digital audio signal from the audio encoding circuit 102 or a digital audio signal from the Bluetooth receiving module 201 according to the operation of the button by the user. Perform speech recognition processing.
  • a button-type control terminal may be disposed on the system master micro-control unit 206.
  • the system master micro-control unit 206 transmits the digital audio from the audio encoding circuit 102 to the main control integrated circuit 205 according to the operation of the button by the user.
  • the command of the signal or the instruction of the digital audio signal from the Bluetooth receiving module 201; the main control integrated circuit 205 selects the digital audio signal from the audio encoding circuit 102 or the number from the Bluetooth receiving module 201 according to the instruction of the system master micro control unit 206.
  • the audio signal is subjected to speech recognition processing. This is also the improvement of the system master control micro control unit in the embodiment of the present invention.
  • the voice recognition system since the voice recognition system includes a microphone array link and a Bluetooth link two voice input links, the voice link is selected in two links, wherein the Bluetooth chain
  • the road can realize the reception of long-distance voice and realize multi-point voice control, so that multiple long-distance voices can be recognized, so that the user can better understand the superiority of voice recognition.

Abstract

提供了一种语音识别系统和方法，其中语音识别系统包括：麦克风阵列（101）、音频编码电路（102）、蓝牙发射模块（202）、蓝牙接收模块（201）、主控集成电路（205）；其中麦克风阵列（101）用于接收语音信号并转换成模拟音频信号后输出给音频编码电路（102）；音频编码电路（102）用于将所接收的模拟音频信号转换成数字音频信号后输出给主控集成电路（205）；蓝牙发射模块（202）用于接收语音信号并转换成数字音频信号后通过蓝牙方式发送给蓝牙接收模块（201）；蓝牙接收模块（201）用于将所接收的数字音频信号发送给主控集成电路（205）；主控集成电路（205）用于选择来自音频编码电路（102）的数字音频信号或来自蓝牙接收模块（201）的数字音频信号进行语音识别处理。所述语音识别系统和方法解决了只有麦克风阵列作为音频输入的语音识别系统无法对远距离语音进行识别的问题。

Description

一种语音识别系统和方法 技术领域
本发明涉及语音识别技术领域，特别涉及一种语音识别系统和方法。
发明背景
目前多种智能音视频设备都添加了语音识别功能。图1是现有的一种音视频设备的组成结构的示意图。如图1所示，该音视频设备包括：麦克风阵列101、音频编码电路102、摄像头103、视频处理电路104、主控集成电路105、系统主控微控制单元（系统主控MCU）106、扬声器107及显示屏108。
其中，麦克风阵列101负责语音信号的拾取并转换成模拟音频信号后输出给音频编码电路102，音频编码电路102将从麦克风阵列101接收的模拟音频信号进行数字编码，然后输出给主控集成电路105；摄像头103用于捕获视频信号并输出给视频处理电路104，视频处理电路104用于对摄像头103输出的信号进行编码处理后输出给主控集成电路105；主控集成电路105汇集视频信号和音频信号后，合成音视频数据流输出给系统主控微控制单元106。系统主控微控制单元106为该音视频设备的核心器件，负责音视频数据链路的管理。从系统主控微控制单元106输出的音频信号通过音频扬声器107变成声音信号，从系统主控微控制单元106输出的视频信号通过显示屏108进行显示。此外，图1所示的音视频设备还包括作为外围接口的USB接口和负责整个系统的稳定供电的电源电路等，这里不再一一赘述。
在现有的如图1所示的具有语音识别功能的音视频设备中，不论采用全指向麦克风阵列还是采用单指向麦克风阵列，都有一定的识别距离，所以只能进行近距离语音识别，而对远距离语音无能为力。
发明内容
本发明提供了一种语音识别系统和方法，以解决只有麦克风阵列作为音频输入的语音识别系统无法对远距离语音进行识别的问题。
为达到上述目的，本发明的技术方案是这样实现的：
本发明公开了一种语音识别系统，包括：麦克风阵列、音频编码电路、主控集成电路、蓝牙接收模块和蓝牙发射模块，其中：
麦克风阵列，用于接收语音信号并转换成模拟音频信号后输出给音频编码电路；
音频编码电路，用于将所接收的模拟音频信号转换成数字音频信号后输出给主控集成电路；
蓝牙发射模块，用于接收语音信号并转换成数字音频信号后通过蓝牙方式发送给蓝牙接收模块；
蓝牙接收模块，用于将所接收的数字音频信号发送给主控集成电路；
主控集成电路，用于选择接收来自音频编码电路的数字音频信号或来自蓝牙接收模块的数字音频信号进行语音识别处理。
在上述语音识别系统中，具有一个蓝牙接收模块和一个以上的蓝牙发射模块。
在上述语音识别系统中，所述主控集成电路具有按键，所述主控集成电路根据用户对该按键的操作选择来自音频编码电路的数字音频信号或来自蓝牙接收模块的数字音频信号进行语音识别处理。
上述语音识别系统还包括：系统主控微控制单元，用于接收来自主控集成电路的音频数据流；
该系统主控微控制单元具有按键，该系统主控微控制单元根据用户对该按键的操作向主控集成电路发送选择来自音频编码电路的数字音频信号的指令或选择来自蓝牙接收模块的数字音频信号的指令；
主控集成电路根据系统主控微控制单元的指令选择来自音频编码电路的数字音频信号或来自蓝牙接收模块的数字音频信号进行语音识别处理。
本发明还公开了一种语音识别的方法，该方法包括：
通过麦克风阵列接收语音信号并转换成模拟音频信号，然后将该模拟音频信号转换成数字音频信号，得到第一路数字音频信号；
通过蓝牙音频链路接收语音信号并转换成数字音频信号，得到第二路数字音频信号；
选择第一路数字音频信号或第二路数字音频信号进行语音识别处理。
在上述方法中，所述蓝牙音频链路包括：蓝牙发射模块和蓝牙接收模块；
所述通过蓝牙音频链路接收语音信号并转换成数字音频信号包括：通过蓝牙发射模块接收语音信号并转换成数字音频信号后发送给蓝牙接收模块，蓝牙接收模块将所接收的数字音频信号作为所述第二路数字音频信号输出。
所述蓝牙音频链路包括：一个以上的蓝牙发射模块和一个蓝牙接收模块。
在上述方法中，所述选择第一路数字音频信号或第二路数字音频信号进行语音识别处理包括：
根据用户的按键操作选择第一路数字音频信号或第二路数字音频信号，并对所选择的数字音频信号进行语音识别处理。
由上述可见，在本发明的方案中，由于语音识别系统包括麦克风阵列链路和蓝牙链路两路语音输入链路，在进行语音识别时在两路链路中进行选择，其中的蓝牙链路可以实现远距离语音的接收，因此可以对远距离的语音进行识别。
附图简要说明
图1是现有的一种音视频设备的组成结构的示意图；
图2为本发明实施例中的包含语音识别系统的音视频设备的组成结构的示意图。
实施本发明的方式
本发明中，通过麦克风阵列接收语音信号并转换成模拟音频信号，然后将该模拟音频信号转换成数字音频信号，得到第一路数字音频信号；并且通过蓝牙音频链路接收语音信号并转换成数字音频信号，得到第二路数字音频信号；然后选择第一路数字音频信号或第二路数字音频信号进行语音识别处理。这样，对于较近的一些语音可以通过麦克风阵列进行拾取，而对于较远区域的语音，则可以通过蓝牙链路实现接收，因此解决了只有麦克风阵列作为音频输入的语音识别系统无法对远距离语音进行识别的问题。
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。
图2为本发明实施例中的包含语音识别系统的音视频设备的组成结构的示意图。如图2所示，该系统包括：麦克风阵列101、音频编码电路102、摄像头103、视频处理电路104、主控集成电路205、系统主控微控制单元206、扬声器107、显示屏108、蓝牙接收模块201和蓝牙发射模块202。这里蓝牙发射模块202的个数为一个或多个，图2中示意出了多个蓝牙发射模块202。另外由于本发明的实施例中对主控集成电路和系统主控微控制单元的功能都进行了改进，因此采用了与图1中不同的附图标记。
其中，麦克风阵列101，用于接收语音信号并转换成模拟音频信号后输出给音频编码电路102。音频编码电路102，用于将所接收的模拟音频信号转换成数字音频信号后输出给主控集成电路205。摄像头103用于捕获视频信号并输出给视频处理电路104，视频处理电路104用于对摄像头103输出的信号进行编码处理后输出给主控集成电路205；
蓝牙发射模块202，用于接收语音信号并转换成数字音频信号后通过蓝牙方式发送给蓝牙接收模块201；蓝牙接收模块201，用于将所接收的数字音频信号发送给主控集成电路205；
主控集成电路205，用于选择来自音频编码电路102的数字音频信号或来自蓝牙接收模块201的数字音频信号进行语音识别处理。即主控集成电路205先在来自音频编码电路102的数字音频信号和来自蓝牙接收模块201的数字音频信号之间进行选择，然后将选择的数字音频信号与来自视频处理电路104的数字视频信号汇集，合成音视频数据流后输出给系统主控微控制单元206。系统主控微控制单元206负责音视频数据链路的管理。从系统主控微控制单元206输出的音频信号通过音频扬声器107变成声音信号，从系统主控微控制单元206输出的视频信号通过显示屏108进行显示。
可见，在图2所示的实施例中有两条音频输入链路，分别为麦克风阵列音频链路和蓝牙音频链路。其中，麦克风阵列音频链路包括：麦克风阵列101和音频编码电路102，麦克风阵列101接收语音信号并转换成模拟音频信号后输出给音频编码电路102，音频编码电路102将所接收的模拟音频信号转换成数字音频信号后作为第一路数字音频信号输出给主控集成电路205。蓝牙音频链路包括：蓝牙发射模块202和蓝牙接收模块201；通过蓝牙发射模块202接收语音信号并转换成数字音频信号后发送给蓝牙接收模块201，蓝牙接收模块201将所接收的数字音频信号作为第二路数字音频信号输出给主控集成电路205。主控集成电路205在第一路数字音频信号和第二路数字音频信号之间进行选择。
在本发明的上述实施例中，保留了麦克风阵列，以实现近距离的语音识别。在此基础上增加了蓝牙语音输入方式，以实现远程语音识别。蓝牙传输技术支持一对多的通信，即可以设置一个蓝牙接收模块和多个的蓝牙发射模块。实践中可以根据需要配备多个蓝牙发射模块，以实现多点语音识别。由于用蓝牙方式可以远距离传输信号，故本系统可以进行远程语音识别。
在本发明的实施例中，可以通过按键控制主控集成电路205的对数字音频信号的选择。
例如，可以在主控集成电路205上设置一个按键式的控制端，主控集成电路205根据用户对该按键的操作选择来自音频编码电路102的数字音频信号或来自蓝牙接收模块201的数字音频信号进行语音识别处理。
或者，也可以在系统主控微控制单元206上设置按键式的控制端，系统主控微控制单元206根据用户对该按键的操作向主控集成电路205发送选择来自音频编码电路102的数字音频信号的指令或选择来自蓝牙接收模块201的数字音频信号的指令；主控集成电路205根据系统主控微控制单元206的指令选择来自音频编码电路102的数字音频信号或来自蓝牙接收模块201的数字音频信号进行语音识别处理。本发明实施例中对系统主控微控制单元的改进也正是在于此。
综上所述，在本发明的方案中，由于语音识别系统包括麦克风阵列链路和蓝牙链路两路语音输入链路，在进行语音识别时在两路链路中进行选择，其中的蓝牙链路可以实现远距离语音的接收以及实现多点语音控制，因此可以对多个远距离的语音进行识别，使用户更好的体会语音识别的优越性。以上所述仅为本发明的较佳实施例而已，并非用于限定本发明的保护范围。凡在本发明的精神和原则之内所作的任何修改、等同替换、改进等，均包含在本发明的保护范围内。

Claims (8)

  1. 一种语音识别系统，其特征在于，包括：麦克风阵列、音频编码电路、主控集成电路、蓝牙接收模块和蓝牙发射模块，其中：
    麦克风阵列，用于接收语音信号并转换成模拟音频信号后输出给音频编码电路；
    音频编码电路，用于将所接收的模拟音频信号转换成数字音频信号后输出给主控集成电路；
    蓝牙发射模块，用于接收语音信号并转换成数字音频信号后通过蓝牙方式发送给蓝牙接收模块；
    蓝牙接收模块，用于将所接收的数字音频信号发送给主控集成电路；
    主控集成电路，用于选择来自音频编码电路的数字音频信号或来自蓝牙接收模块的数字音频信号进行语音识别处理。
  2. 根据权利要求1所述的语音识别系统，其特征在于：该系统具有一个蓝牙接收模块和一个以上的蓝牙发射模块。
  3. 根据权利要求1或2所述的语音识别系统，其特征在于，所述主控集成电路具有按键，所述主控集成电路根据用户对该按键的操作选择来自音频编码电路的数字音频信号或来自蓝牙接收模块的数字音频信号进行语音识别处理。
  4. 根据权利要求1或2所述的语音识别系统，其特征在于，该语音识别系统还包括：系统主控微控制单元，用于接收来自主控集成电路的音频数据流；
    该系统主控微控制单元具有按键，该系统主控微控制单元根据用户对该按键的操作向主控集成电路发送选择来自音频编码电路的数字音频信号的指令或选择来自蓝牙接收模块的数字音频信号的指令；
    主控集成电路根据系统主控微控制单元的指令选择来自音频编码电路的数字音频信号或来自蓝牙接收模块的数字音频信号进行语音识别处理。
  5. 一种语音识别的方法，其特征在于，该方法包括：
    通过麦克风阵列接收语音信号并转换成模拟音频信号，然后将该模拟音频信号转换成数字音频信号，得到第一路数字音频信号；
    通过蓝牙音频链路接收语音信号并转换成数字音频信号，得到第二路数字音频信号；
    选择第一路数字音频信号或第二路数字音频信号进行语音识别处理。
  6. 根据权利要求5所述的语音识别方法，其特征在于，所述蓝牙音频链路包括：蓝牙发射模块和蓝牙接收模块；
    所述通过蓝牙音频链路接收语音信号并转换成数字音频信号包括：通过蓝牙发射模块接收语音信号并转换成数字音频信号后发送给蓝牙接收模块，蓝牙接收模块将所接收的数字音频信号作为所述第二路数字音频信号输出。
  7. 根据权利要求6所述的方法，其特征在于，所述蓝牙音频链路包括：一个以上的蓝牙发射模块和一个蓝牙接收模块。
  8. 根据权利要求5或6所述的语音识别方法，其特征在于，所述选择对第一路数字音频信号或二路数字音频信号进行语音识别处理包括：
    根据用户的按键操作选择第一路数字音频信号或第二路数字音频信号，并对所选择的数字音频信号进行语音识别处理。
PCT/CN2013/081432 2012-08-15 2013-08-14 一种语音识别系统和方法 WO2014026605A1 (zh)

Priority Applications (2)

Application Number Priority Date Filing Date Title
US14/415,813 US20150213797A1 (en) 2012-08-15 2013-08-14 Voice Recognition System And Method
KR1020157002167A KR20150032731A (ko) 2012-08-15 2013-08-14 음성 인식 시스템 및 방법

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201210290828.6 2012-08-15
CN201210290828.6A CN102820032B (zh) 2012-08-15 2012-08-15 一种语音识别系统和方法

Publications (1)

Publication Number Publication Date
WO2014026605A1 true WO2014026605A1 (zh) 2014-02-20

Family

ID=47304117

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2013/081432 WO2014026605A1 (zh) 2012-08-15 2013-08-14 一种语音识别系统和方法

Country Status (4)

Country Link
US (1) US20150213797A1 (zh)
KR (1) KR20150032731A (zh)
CN (1) CN102820032B (zh)
WO (1) WO2014026605A1 (zh)

Families Citing this family (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102820032B (zh) * 2012-08-15 2014-08-13 歌尔声学股份有限公司 一种语音识别系统和方法
CN103293691A (zh) * 2013-06-09 2013-09-11 歌尔声学股份有限公司 具有语音识别功能的3d眼镜
CN103928025B (zh) * 2014-04-08 2017-06-27 华为技术有限公司 一种语音识别的方法及移动终端
CN106507244A (zh) * 2016-12-23 2017-03-15 深圳先进技术研究院 一种中控系统
US10373630B2 (en) * 2017-03-31 2019-08-06 Intel Corporation Systems and methods for energy efficient and low power distributed automatic speech recognition on wearable devices
CN108461083A (zh) * 2018-03-23 2018-08-28 北京小米移动软件有限公司 电子设备主板、音频处理方法、装置和电子设备
CN108616790B (zh) * 2018-04-24 2021-01-26 京东方科技集团股份有限公司 一种拾音放音电路和系统、拾音放音切换方法
KR20200076441A (ko) 2018-12-19 2020-06-29 삼성전자주식회사 전자 장치 및 그의 제어 방법
CN111402890A (zh) * 2020-03-17 2020-07-10 常州市贝叶斯智能科技有限公司 一种用于机器人语音识别和播放的电路系统
CN114170781A (zh) * 2021-11-18 2022-03-11 广州大学 一种智能插座控制系统、方法、装置及存储介质

Citations (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101286769A (zh) * 2008-03-14 2008-10-15 深圳创维－Rgb电子有限公司 一种蓝牙声控点播系统
CN201142704Y (zh) * 2007-11-26 2008-10-29 厉天福 一种车载多媒体免提音频装置
CN101308602A (zh) * 2008-04-16 2008-11-19 深圳创维－Rgb电子有限公司 一种蓝牙声控电视机系统
JP2008306769A (ja) * 2008-09-11 2008-12-18 Denso Corp ハンズフリー装置
CN201254147Y (zh) * 2008-07-22 2009-06-10 深圳市北科瑞声科技有限公司 应用于汽车电子通讯和多媒体娱乐的人机交互系统
CN101689367A (zh) * 2007-05-31 2010-03-31 摩托罗拉公司 配置用于语音识别的音频处理路径的方法和系统
CN201749668U (zh) * 2010-06-25 2011-02-16 大陆汽车亚太管理(上海)有限公司 语音操作的车载免提设备
CN202077092U (zh) * 2011-04-29 2011-12-14 武汉新科泰电子有限公司 车载语音控制蓝牙免提装置
CN102820032A (zh) * 2012-08-15 2012-12-12 歌尔声学股份有限公司 一种语音识别系统和方法
CN202796042U (zh) * 2012-08-15 2013-03-13 歌尔声学股份有限公司 一种语音识别系统

Family Cites Families (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN201177970Y (zh) * 2007-11-23 2009-01-07 厉天福 一种车载多媒体影音装置
US20100088096A1 (en) * 2008-10-02 2010-04-08 Stephen John Parsons Hand held speech recognition device
US20100332236A1 (en) * 2009-06-25 2010-12-30 Blueant Wireless Pty Limited Voice-triggered operation of electronic devices
US8626498B2 (en) * 2010-02-24 2014-01-07 Qualcomm Incorporated Voice activity detection based on plural voice activity detectors
WO2012009689A1 (en) * 2010-07-15 2012-01-19 Aliph, Inc. Wireless conference call telephone
WO2012063103A1 (en) * 2010-11-12 2012-05-18 Nokia Corporation An Audio Processing Apparatus
CN105229737B (zh) * 2013-03-13 2019-05-17 寇平公司 噪声消除麦克风装置
TWI543635B (zh) * 2013-12-18 2016-07-21 jing-feng Liu Speech Acquisition Method of Hearing Aid System and Hearing Aid System

Patent Citations (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101689367A (zh) * 2007-05-31 2010-03-31 摩托罗拉公司 配置用于语音识别的音频处理路径的方法和系统
CN201142704Y (zh) * 2007-11-26 2008-10-29 厉天福 一种车载多媒体免提音频装置
CN101286769A (zh) * 2008-03-14 2008-10-15 深圳创维－Rgb电子有限公司 一种蓝牙声控点播系统
CN101308602A (zh) * 2008-04-16 2008-11-19 深圳创维－Rgb电子有限公司 一种蓝牙声控电视机系统
CN201254147Y (zh) * 2008-07-22 2009-06-10 深圳市北科瑞声科技有限公司 应用于汽车电子通讯和多媒体娱乐的人机交互系统
JP2008306769A (ja) * 2008-09-11 2008-12-18 Denso Corp ハンズフリー装置
CN201749668U (zh) * 2010-06-25 2011-02-16 大陆汽车亚太管理(上海)有限公司 语音操作的车载免提设备
CN202077092U (zh) * 2011-04-29 2011-12-14 武汉新科泰电子有限公司 车载语音控制蓝牙免提装置
CN102820032A (zh) * 2012-08-15 2012-12-12 歌尔声学股份有限公司 一种语音识别系统和方法
CN202796042U (zh) * 2012-08-15 2013-03-13 歌尔声学股份有限公司 一种语音识别系统

Also Published As

Publication number Publication date
CN102820032A (zh) 2012-12-12
CN102820032B (zh) 2014-08-13
US20150213797A1 (en) 2015-07-30
KR20150032731A (ko) 2015-03-27

Similar Documents

Publication Publication Date Title
WO2014026605A1 (zh) 一种语音识别系统和方法
US20140037262A1 (en) Data storage device and storage medium
CN108260051A (zh) 语音遥控系统、便携式传输设备及智能设备
RU2012121949A (ru) Система видеоконтроля и способ управления им
JP2012178695A5 (zh)
CN102999277A (zh) 一种对信号进行处理的方法及电子设备
CN108055610A (zh) 智能音箱
CN109716738B (zh) 便携终端装置、电视接收装置和来电通知方法
WO2016140380A1 (ko) 셀피 스틱을 이용한 고음질 녹화영상 생성 장치 및 방법
CN201928380U (zh) 一种带摄像头的遥控器和视讯接收终端
KR101910659B1 (ko) 디지털 영상장치 및 그 제어방법
CN111713119A (zh) 耳机、耳机系统和耳机系统中的方法
CN209545705U (zh) 一种矿用本安型摄像仪
CN109859748B (zh) 基于语音自动识别的对讲机实现系统及方法
CN208908486U (zh) 云台系统
CN103136924B (zh) 一种多功能遥控装置
KR20160107430A (ko) 셀피 스틱을 이용한 고음질 녹화영상 생성 장치
CN202231785U (zh) 摄像装置控制电路和摄像系统
CN106170109A (zh) 一种影院用无线环绕音箱
CN105491411B (zh) 具有信号转换功能的电视系统
CN104468933A (zh) 利用移动网络实现单人和多人语音留言的方法及设备
KR100769672B1 (ko) 화상 통신이 가능한 이동통신단말기
CN203708256U (zh) 语音数据红外传输装置
CN201263195Y (zh) 远程数字控制图像监控系统
CN202796042U (zh) 一种语音识别系统

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 13829220

Country of ref document: EP

Kind code of ref document: A1

WWE Wipo information: entry into national phase

Ref document number: 14415813

Country of ref document: US

ENP Entry into the national phase

Ref document number: 20157002167

Country of ref document: KR

Kind code of ref document: A

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 13829220

Country of ref document: EP

Kind code of ref document: A1