WO2013127367A1 - 一种即时通信的语音识别方法和终端 - Google Patents

一种即时通信的语音识别方法和终端 Download PDF

Info

Publication number
WO2013127367A1
WO2013127367A1 PCT/CN2013/072086 CN2013072086W WO2013127367A1 WO 2013127367 A1 WO2013127367 A1 WO 2013127367A1 CN 2013072086 W CN2013072086 W CN 2013072086W WO 2013127367 A1 WO2013127367 A1 WO 2013127367A1
Authority
WO
WIPO (PCT)
Prior art keywords
information
voice
terminal
voice information
played
Prior art date
Application number
PCT/CN2013/072086
Other languages
English (en)
French (fr)
Inventor
路依莎
Original Assignee
腾讯科技（深圳）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 腾讯科技（深圳）有限公司 filed Critical 腾讯科技（深圳）有限公司
Priority to JP2014559078A priority Critical patent/JP2015515643A/ja
Priority to US14/382,122 priority patent/US9263029B2/en
Priority to KR1020147027277A priority patent/KR101633208B1/ko
Publication of WO2013127367A1 publication Critical patent/WO2013127367A1/zh

Links

Classifications

    • G—PHYSICS
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
    • G10L15/00—Speech recognition
    • G—PHYSICS
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
    • G10L13/00—Speech synthesis; Text to speech systems
    • G—PHYSICS
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
    • G10L15/00—Speech recognition
    • G10L15/22—Procedures used during a speech recognition process, e.g. man-machine dialogue
    • G—PHYSICS
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
    • G10L21/00—Speech or voice signal processing techniques to produce another audible or non-audible signal, e.g. visual or tactile, in order to modify its quality or its intelligibility
    • G10L21/02—Speech enhancement, e.g. noise reduction or echo cancellation
    • G10L21/0208—Noise filtering
    • G10L21/0216—Noise filtering characterised by the method used for estimating noise
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L51/00—User-to-user messaging in packet-switching networks, transmitted according to store-and-forward or real-time protocols, e.g. e-mail
    • H04L51/04—Real-time or near real-time messaging, e.g. instant messaging [IM]
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L51/00—User-to-user messaging in packet-switching networks, transmitted according to store-and-forward or real-time protocols, e.g. e-mail
    • H04L51/07—User-to-user messaging in packet-switching networks, transmitted according to store-and-forward or real-time protocols, e.g. e-mail characterised by the inclusion of specific contents
    • H04L51/10—Multimedia information
    • G—PHYSICS
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
    • G10L15/00—Speech recognition
    • G10L15/26—Speech to text systems
    • G—PHYSICS
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; 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
    • G—PHYSICS
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
    • G10L15/00—Speech recognition
    • G10L15/22—Procedures used during a speech recognition process, e.g. man-machine dialogue
    • G10L2015/225—Feedback of the input speech
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04M—TELEPHONIC COMMUNICATION
    • H04M2203/00—Aspects of automatic or semi-automatic exchanges
    • H04M2203/45—Aspects of automatic or semi-automatic exchanges related to voicemail messaging
    • H04M2203/4536—Voicemail combined with text-based messaging
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04M—TELEPHONIC COMMUNICATION
    • H04M2250/00—Details of telephonic subscriber devices
    • H04M2250/74—Details of telephonic subscriber devices with voice recognition means

Definitions

  • the present invention relates to the field of communications, and in particular, to a voice recognition method and terminal for instant messaging. Background technique
  • chat tools to communicate with friends.
  • voice input is becoming more and more popular, and voice input is free from the traditional virtual keyboard input and repeated click operation, and the communication between users is faster and smoother.
  • voice input functions such as PC end QQ, mobile terminal WeChat intercom, mobile QQ voice input, m chat intercom and the like.
  • voice input functions such as PC end QQ, mobile terminal WeChat intercom, mobile QQ voice input, m chat intercom and the like.
  • the receiver when the voice input is based on instant communication, the receiver is not convenient to directly play the voice.
  • how to make the recipient directly obtain the voice content is a problem that has been concerned by people in the field. Summary of the invention
  • the embodiment of the present invention provides a voice recognition method and terminal for instant communication.
  • the technical solution is as follows:
  • An embodiment of the present invention provides a voice recognition method for instant communication, where the method includes: receiving voice information input by a user;
  • the voice information is recognized as text information.
  • the identifying the voice information as text information includes: Transmitting the voice information to a voice recognition server in the cloud, so that the voice recognition server identifies the voice information as text information;
  • the voice information is identified as text information, and specifically includes:
  • the voice information is voice-recognized through a voice recognition module built in the terminal to obtain text information.
  • the current environment information is specifically an operation instruction of the user, and the determining, according to the current environment information, whether the voice information needs to be played, specifically includes:
  • the operation instruction of the user is an instruction to acquire text information, it is determined that the voice is not required to be played;
  • the current environment information specifically includes the hardware information of the terminal itself, and the determining, according to the current environment information, whether the voice information needs to be played, specifically includes:
  • the current environment information includes the current noise information, and the determining, according to the current environment information, whether the voice information needs to be played, specifically includes:
  • the terminal is a mobile terminal or a PC terminal.
  • the embodiment of the invention further provides a terminal, where the terminal includes:
  • An obtaining module configured to receive voice information input by a user
  • a determining module configured to obtain current environment information, and determine, according to the current environment information, whether the voice information needs to be played;
  • An identification module configured to: when the determination result of the determining module is negative, identify the voice information For text information.
  • the identification module specifically includes a sending unit and a receiving unit
  • the sending unit is configured to: when the determining result of the determining module is negative, send the voice information to a voice recognition server in the cloud, so that the voice recognition server recognizes the voice information as text information;
  • the receiving unit is configured to receive the text information recognized by the voice recognition server.
  • the identifying module specifically includes: when the determining result of the determining module is negative, identifying the voice information as text information by using a voice recognition module built in the terminal.
  • the determining module specifically includes an obtaining unit and a determining unit
  • the obtaining unit is configured to acquire an operation instruction of the user
  • the determining unit is configured to: when the operation instruction of the user is an instruction to obtain text information, determine that the voice information piece is not required to be played; when the operation instruction of the user is not an instruction to obtain text information, It is determined that the voice information piece needs to be played.
  • the determining module specifically includes an obtaining unit and a determining unit
  • the obtaining unit is configured to acquire hardware information of the terminal itself
  • the determining unit is configured to: when the hardware information of the terminal itself meets the condition for playing the voice information, determine that the voice information piece needs to be played; when the hardware information of the terminal itself does not satisfy the playing of the voice information When the condition of the information is determined, it is judged that the voice information piece does not need to be played.
  • the determining module specifically includes an obtaining unit and a determining unit
  • the acquiring unit is configured to acquire current noise information
  • the determining unit is configured to: when the current noise information is within a preset range, determine that the voice information piece needs to be played; when the current noise information is not within a preset range, determine The voice information piece needs to be played.
  • the terminal is a mobile terminal or a PC terminal.
  • the technical solution provided by the embodiment of the present invention has the beneficial effects of: providing voice recognition function to the voice receiver when the terminal receives the voice information of the instant communication, so as to help the receiver to know the other party in an inconvenient situation.
  • Expressed content For example, in public, when it is inconvenient to play a voice, or in the absence of a playback device, when the voice cannot be played, the user can quickly know the voice content.
  • FIG. 1 is a flowchart of a voice recognition method based on instant communication provided in Embodiment 1 of the present invention
  • FIG. 2 is a flowchart of a voice recognition method based on instant communication provided in Embodiment 2 of the present invention
  • FIG. 3 is a second embodiment of the present invention
  • FIG. 4 is a schematic diagram of voice recognition of instant messaging under the PC in the second embodiment of the present invention
  • FIG. 5 is a schematic structural diagram of a terminal provided in Embodiment 3 of the present invention.
  • FIG. 6 is a schematic structural diagram of a determining module in a terminal provided in Embodiment 3 of the present invention. detailed description
  • an embodiment of the present invention provides a voice recognition method based on instant communication, where the method includes:
  • Step 101 Receive voice information input by a user
  • Step 102 Obtain current environment information, and determine, according to current environment information, whether voice information needs to be played.
  • Step 103 When it is determined that the voice information is not required to be played, the voice information is recognized as text information.
  • the method provided by the embodiment of the present invention provides a voice recognition function for the voice receiver when the terminal receives the voice information of the instant communication, so as to help the receiver to know the content to be expressed by the receiver in an inconvenient manner. For example, in public, when it is inconvenient to play a voice, or in the absence of a playback device, when the voice cannot be played, the user can quickly know the voice content.
  • Example 2 when it is inconvenient to play a voice, or in the absence of a playback device, when the voice cannot be played, the user can quickly know the voice content.
  • an embodiment of the present invention provides a voice recognition method for instant messaging, where the method includes:
  • Step 201 Receive voice information input by a user
  • the terminal receives the voice information input by the user.
  • the application scenario can input voice information for the user in the instant scene of the Internet application, or input voice information for the user in the chat scenario.
  • the terminal in the embodiment of the present invention is a mobile terminal or a PC terminal.
  • the mobile terminal can be a mobile phone, a PDA (Personal Digital Assistant), and a MID (Mobile Internet Devices).
  • Step 202 Obtain current environment information.
  • the current environment information in the embodiment of the present invention may be the hardware information of the terminal itself, the operation instruction of the user, the current noise information, and the like.
  • the specific content of the current environmental information is not limited in the embodiment of the present invention.
  • the hardware information of the terminal itself includes, but is not limited to, hardware device information currently installed by the terminal, such as an audio input or output device connected through an interface, and the hardware information may also include driving information of the audio input or output device, etc., such as audio coding. Decoder and audio device drivers, etc.
  • the operation instruction of the user may be any operation instruction to the terminal. According to the setting of the technician during development, different operation instructions may correspond to different functions. For example, the click operation on the voice information may be used to play the voice information. The operation command, and the click operation for the corresponding information of the voice information to obtain the text information may be an operation instruction for acquiring the text information.
  • the current noise information refers to the noise information of the environment in which the terminal is located. If the terminal is currently in the conference room, the current noise information refers to the noise information in the conference room. Correspondingly, the current environment information is obtained to obtain the current noise information, which may be performed by the microphone of the terminal, and the specific process is similar to the process of acquiring the voice, and details are not described herein.
  • the type of environmental information obtained may be set by the technician by default, and may also be adjusted by the user during use. For different types of environmental information types, the specific judgment process is different. For details, see the description in step 203.
  • Step 203 Determine whether the voice information needs to be played according to the current environment information, if not, execute step 204, and if yes, execute step 206;
  • voice input can bring users a faster and smoother communication process, but in many scenarios (such as conference rooms, noisy environments or the other party does not have headphones or players, or the voice content is relatively private) It is not convenient for the receiver to play the voice.
  • the voice information can be recognized as text information, which is convenient for the recipient to select, the receiver can select to play the voice information, or can select to view the recognized text information. .
  • Method 1 The current environmental information is an operation instruction of the user
  • the method specifically includes: determining whether the operation instruction is an instruction for acquiring the text information, and when the operation instruction is an instruction for acquiring the text information, determining that the voice information is not required to be played, and performing the step When the operation instruction of the user is not an instruction to acquire the text information, it is determined that the voice information needs to be played, and the operation of step 206 is performed.
  • the user reads the voice information received on the terminal by performing an operation instruction, and the operation instruction may be a click operation or a touch operation, which is not limited herein.
  • the terminal determines, according to the operation instruction of the user, the manner in which the user selects the information to be obtained. After receiving the operation instruction of the user, the terminal determines, according to the operation instruction, whether the terminal needs to play the voice information, if the user does not need to play the voice information, The voice information needs to be recognized as text information and provided to the user; if the user needs to play the voice information, the terminal can directly play the voice information to the user, and does not need to perform other special processing operations.
  • buttons A and B are set on the terminal, and characters such as "voice” and “horn shape” are displayed on the button A, and characters such as "text” and “ABC” are displayed on the button B, wherein the user clicks or touches the button.
  • A it indicates that the voice information is obtained, and the voice information is played;
  • B it indicates that the text information is obtained, and the text information is displayed.
  • Method 2 The current environmental information is the hardware information of the terminal itself;
  • the hardware information that the terminal satisfies the playing voice information includes at least an audio codec and an audio output device.
  • Determining whether the voice information needs to be played according to the current environment information specifically: determining whether the hardware condition of the terminal itself has an audio decoder and an audio output device, and when the hardware information of the terminal itself has an audio codec and an audio output device, The hardware information of the terminal itself satisfies the condition for playing the voice information. At this time, it is determined that the terminal needs to play the voice information, and the operation of step 206 is performed; when the hardware information of the terminal does not have the audio codec, or the audio output device is not provided. When the audio codec and the audio output device are not provided, the hardware information of the terminal does not satisfy the condition for playing the voice information, and it is determined that the voice information does not need to be played, and the operation of step 204 is performed.
  • Method 3 The current environmental information is current noise information
  • the present invention presets a certain noise range, such as a preset range of 30 decibels to 90 decibels, and determines whether it is necessary to play the voice information according to the current environmental information, specifically: determining whether the current noise information is within a preset range; If the current noise information is within the preset range, it is determined that the message needs to be played. If the current noise information is not in the preset range, it indicates that the current environment is a silent environment or a particularly noisy environment, and it is determined that the voice information is not required to be played, and the operation of step 204 is performed.
  • a certain noise range such as a preset range of 30 decibels to 90 decibels
  • the method of the first mode, the second mode, and the third mode is a singular relationship.
  • the implementation manner of the first mode may be adopted, or the implementation manner of the second method may be adopted, or the implementation manner of the third method may be adopted, or three implementation manners may be used.
  • the priority of the implementation manner is implemented according to the priority level.
  • the adoption of the implementation manner may be set by a technician by default, and may also be adjusted by the user during use.
  • Step 204 Identify the voice information as text information.
  • the method for identifying the obtained voice information as the text information provided by the embodiment of the present invention may be identified in the cloud, or the identification module may be built in the local area, which is not limited by the present invention.
  • the terminal sends the voice information to the voice recognition server in the cloud, and the voice recognition server performs voice recognition, and the cloud refers to the network, and the voice recognition server in the cloud refers to the network.
  • the voice recognition server then transmits the recognition result to the terminal, and the terminal receives the text information recognized by the voice recognition server.
  • the terminal transmits the voice information to a designated voice recognition server on the network, and the voice recognition server can identify one or more voice messages.
  • the terminal when the local built-in identification module recognizes the voice information as the text information, the terminal performs the voice recognition through the voice recognition module built in the terminal to obtain the text information.
  • the voice recognition module when the terminal installs the instant communication tool, the voice recognition module is already built in.
  • the terminal wants to recognize the voice information, the terminal can directly use the module to perform voice recognition on the voice information to be recognized, and then directly provide the recognition result to the user. Just fine.
  • the voice recognition technology is required to be used in the cloud recognition or the local built-in identification module, for example, google, Baidu, Xunfei, etc., and the voice recognition technology is not limited in the embodiment of the present invention. As long as the voice information can be recognized as text information.
  • Mobile terminal scenario In the chat scenario of instant communication of the mobile terminal, as shown in FIG. 3, after the voice information, a function key of “text” is provided, and when the user clicks the button, the operation instruction of the user is to obtain the text information. Instructed, the mobile terminal recognizes the voice information as text information.
  • PC terminal scenario In the chat scenario of instant communication of the PC terminal, as shown in FIG. 4, after the voice information, a function key of “recognizing into text” is provided, and the user clicks this button to indicate that the user's operation instruction is to obtain text information. The instruction, at this time, the PC terminal recognizes the voice information as text information. Step 205: Display the text information to the user.
  • the text information is displayed on the screen of the terminal. It should be noted that, when the text information is displayed, it can be displayed in a designated area in an independent information form, and can also be displayed on a display area of the voice information, and the in-situ display provides a more intuitive visual effect.
  • Step 206 Play the voice information.
  • the terminal when the terminal determines that the voice information needs to be played, the terminal directly plays the voice information.
  • the method provided by the embodiment of the present invention provides a voice recognition function for the voice receiver when the terminal receives the voice information of the instant communication, so as to help the receiver to know the content to be expressed by the receiver in an inconvenient manner. For example, in public, when it is inconvenient to play a voice, or in the absence of a playback device, when the voice cannot be played, the user can quickly know the voice content.
  • Example 3 In public, when it is inconvenient to play a voice, or in the absence of a playback device, when the voice cannot be played, the user can quickly know the voice content.
  • an embodiment of the present invention provides a terminal, where the terminal includes:
  • the obtaining module 301 is configured to receive voice information input by the user;
  • the determining module 302 is configured to obtain current environment information, and determine, according to the current environment information, whether the voice information needs to be played;
  • the identification module 303 is configured to: when the determination result of the determination module 302 is negative, identify the text information by the voice information.
  • the identification module 303 specifically includes a sending unit and a receiving unit.
  • a sending unit configured to: when the determining result of the determining module 302 is negative, send the voice information to the voice recognition server, so that the voice recognition server identifies the voice information as text information;
  • the receiving unit is configured to receive the text information recognized by the voice recognition server.
  • the identification module 303 specifically includes: when the determination result of the determination module 302 is negative, the voice information is recognized as text information by the voice recognition module built in the terminal.
  • the determining module 302 includes an obtaining unit 3021 and a determining unit 3022, and an obtaining unit 3021, configured to acquire an operation instruction of the user;
  • the determining unit 3022 is configured to: when the user's operation instruction is an instruction to obtain the text information, determine that the voice information piece is not required to be played; and when the user's operation instruction is not an instruction to obtain the text information, determine that the voice information needs to be played.
  • the determining module 302 specifically includes an obtaining unit 3021 and a determining unit 3022;
  • the obtaining unit 3021 is configured to acquire hardware information of the terminal itself.
  • the determining unit 3022 is configured to: when the hardware information of the terminal itself meets the condition for playing the voice information, determine that the voice information needs to be played; when the hardware information of the terminal does not satisfy the condition for playing the voice information, determine that the voice does not need to be played. information.
  • the determining module 302 specifically includes an obtaining unit 3021 and a determining unit 3022;
  • the obtaining unit 3021 is configured to obtain current noise information.
  • the determining unit 3022 is configured to determine that the voice information needs to be played when the current noise information is within the preset range. When the current noise information is not within the preset range, it is determined that the voice information is not required to be played.
  • the terminal is specifically a mobile terminal or a PC terminal.
  • the mobile terminal can be a mobile phone, a PDA (Personal Digital Assistant), and a MID (Mobile Internet Devices).
  • the terminal provided by the embodiment of the present invention provides a voice recognition function for the voice receiver when the terminal receives the voice information of the instant communication, so as to help the receiver to know the content to be expressed by the receiver in an inconvenient manner. For example, in public, when it is inconvenient to play a voice, or in the absence of a playback device, when the voice cannot be played, the user can quickly know the voice content.
  • the terminal provided in this embodiment may be the same as the method embodiment.
  • a person skilled in the art may understand that all or part of the steps of implementing the above embodiments may be completed by hardware, or may be instructed by a program to execute related hardware, and the program may be stored in a computer readable storage medium.
  • the storage medium mentioned may be a read only memory, a magnetic disk or an optical disk or the like.

Landscapes

  • Engineering & Computer Science (AREA)
  • Multimedia (AREA)
  • Acoustics & Sound (AREA)
  • Audiology, Speech & Language Pathology (AREA)
  • Human Computer Interaction (AREA)
  • Physics & Mathematics (AREA)
  • Health & Medical Sciences (AREA)
  • Computational Linguistics (AREA)
  • Signal Processing (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Quality & Reliability (AREA)
  • Telephonic Communication Services (AREA)
  • Telephone Function (AREA)

Abstract

一种即时通信的语音识别方法和终端，属于通信领域。所述方法包括：接收用户输入的语音信息；获取当前的环境信息，并根据所述当前的环境信息判断是否需要播放所述语音信息；判断出不需要播放所述语音信息时，则将所述语音信息识别为文字信息。所述终端包括获取模块、判断模块和识别模块。

Description

说 明 书 一种即时通信的语音识别方法和终端
本申请要求于 2012年 3月 2日提交中国专利局、申请号为 2012100536289、 发明名称为 "一种即时通信的语音识别方法和终端"的中国专利申请的优先权， 其全部内容通过引用结合在本申请中。 技术领域
本发明涉及通信领域， 特别涉及一种即时通信的语音识别方法和终端。 背景技术
随着网络的发展， 越来越多的人们逐渐开始依赖移动装置打发时间、 与朋 友聊天和娱乐消遣， 其中， 移动终端网民中， 近 3/4的用户用聊天工具和好友 交流。 目前主流的聊天工具中， 语音输入越来越流行， 语音输入摆脱了传统虚 拟键盘输入反复点击的操作， 用户之间的沟通更快捷、 更流畅。
目前终端的即时通信工具中大多提供了语音输入的功能， 比如 PC端 QQ、 移动终端的微信对讲、 手机 QQ的语音输入， 米聊的对讲等等。 但是^艮多场景 下， 如在会议室或嘈杂的环境下， 或接收方没有耳机或播放器或语音内容比较 私密等，基于即时通信进行语音输入时，接收方不太方便直接播放语音，此时， 如何让接收方直接获取到语音内容是本领域人员一直关注的问题。 发明内容
为了在即时通信时让接收方直接获取到语音内容， 本发明实施例提供了一 种即时通信的语音识别方法和终端。 所述技术方案如下：
本发明实施例提供了一种即时通信的语音识别方法， 所述方法包括： 接收用户输入的语音信息；
获取当前的环境信息， 并根据所述当前的环境信息判断是否需要播放所述 语音信息；
判断出不需要播放所述语音信息时， 则将所述语音信息识别为文字信息。 其中， 所述将所述语音信息识别为文字信息， 具体包括： 将所述语音信息发送给云端的语音识别服务器，使所述语音识别服务器将 所述语音信息识别为文字信息；
接收所述语音识别服务器识别得到的文字信息。
其中， 所述将语音信息识别为文字信息， 具体包括：
将所述语音信息通过终端内置的语音识别模块进行语音识别，得到文字信 息。
其中， 所述当前的环境信息具体为用户的操作指令， 所述根据所述当前的 环境信息判断是否需要播放所述语音信息， 具体包括：
当所述用户的操作指令是获取文字信息的指令时， 则判断出不需要播放所 述语音；
当所述用户的操作指令不是获取文字信息的指令时， 则判断出需要播放所 述语音信息。
其中， 所述当前的环境信息具体包括终端自身的硬件信息， 所述根据所述 当前的环境信息判断是否需要播放所述语音信息， 具体包括：
当所述终端自身的硬件信息满足播放所述语音信息的条件时， 则判断出需 要播放所述语音信息；
当所述终端自身的硬件信息不满足播放所述语音信息的条件时， 则判断出 不需要播放所述语音信息。
其中， 所述当前的环境信息具体包括当前的噪声信息， 所述根据所述当前 的环境信息判断是否需要播放所述语音信息， 具体包括：
判断所述当前的噪声信息是否在预设的范围内；
当所述当前的噪声信息在预设的范围内， 则判断出需要播放所述语音信 息；
当所述当前的噪声信息不在预设的范围内， 则判断出不需要播放所述语音 信息。
其中， 所述终端为移动终端或 PC终端。
本发明实施例还提供了一种终端， 所述终端包括：
获取模块， 用于接收用户输入的语音信息；
判断模块， 用于获取当前的环境信息， 根据所述当前的环境信息判断是否 需要播放所述语音信息；
识别模块， 用于当所述判断模块的判断结果为否时， 将所述语音信息识别 为文字信息。
其中， 所述识别模块具体包括发送单元和接收单元；
所述发送单元， 用于当所述判断模块的判断结果为否时， 将所述语音信息 发送给云端的语音识别服务器，使所述语音识别服务器将所述语音信息识别为 文字信息；
所述接收单元， 用于接收所述语音识别服务器识别得到的文字信息。 其中， 所述识别模块具体包括： 当所述判断模块的判断结果为否时， 将所 述语音信息通过终端内置的语音识别模块识别为文字信息。
其中， 所述判断模块具体包括获取单元和判断单元，
所述获取单元， 用于获取用户的操作指令；
所述判断单元， 用于当所述用户的操作指令是获取文字信息的指令时， 则 判断出不需要播放所述语音信息件； 当所述用户的操作指令不是获取文字信息 的指令时， 则判断出需要播放所述语音信息件。
其中， 所述判断模块具体包括获取单元和判断单元；
所述获取单元， 用于获取终端自身的硬件信息；
所述判断单元， 用于当所述终端自身的硬件信息满足播放所述语音信息的 条件时， 则判断出需要播放所述语音信息件； 当所述终端自身的硬件信息不满 足播放所述语音信息的条件时， 则判断出不需要播放所述语音信息件。
其中， 所述判断模块具体包括获取单元和判断单元；
所述获取单元， 用于获取当前的噪声信息；
所述判断单元， 用于当所述当前的噪声信息在预设的范围内， 则判断出需 要播放所述语音信息件； 当所述当前的噪声信息不在预设的范围内， 则判断出 不需要播放所述语音信息件。
其中， 所述终端为移动终端或 PC终端。
本发明实施例提供的技术方案带来的有益效果是： 通过终端接收到即时通 信的语音信息时， 为语音接收方提供语音识别的功能， 以帮助接收方在不方便 的情况下正常获知对方要表达的内容。 例如在公共场合， 不方便播放语音时， 或在无播放设备的情景下， 无法播放语音时， 用户能够快捷的获知语音内容。 附图说明
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 需要使用的附图作筒单地介绍， 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。
图 1是本发明实施例 1中提供的基于即时通信的语音识别方法流程图； 图 2是本发明实施例 2中提供的基于即时通信的语音识别方法流程图； 图 3是本发明实施例 2中在移动终端下的即时通信的语音识别示意图； 图 4是本发明实施例 2中在 PC端下的即时通信的语音识别示意图； 图 5是本发明实施例 3中提供的终端的结构示意图；
图 6是本发明实施例 3中提供的终端中判断模块的结构示意图。 具体实施方式
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。
实施例 1
参见图 1 , 本发明实施例提供了一种基于即时通信的语音识别方法， 所述 方法包括：
步骤 101 : 接收用户输入的语音信息；
步骤 102: 获取当前的环境信息， 并根据当前的环境信息判断是否需要播 放语音信息；
步骤 103: 判断出不需要播放所述语音信息时， 则将语音信息识别为文字 信息。
本发明实施例提供的方法， 通过终端接收到即时通信的语音信息时， 为语 音接收方提供语音识别的功能， 以帮助接收方在不方便的情况下正常获知对方 要表达的内容。 例如在公共场合， 不方便播放语音时， 或在无播放设备的情景 下， 无法播放语音时， 用户能够快捷的获知语音内容。 实施例 2
参见图 2, 本发明实施例提供了一种即时通信的语音识别方法， 所述方法 包括：
步骤 201 : 接收用户输入的语音信息；
该步骤中， 终端接收到用户输入的语音信息。 具体地， 本发明实施例中的 应用场景， 可以为用户在互联网应用的即时场景下输入语音信息， 也可以为用 户在聊天场景下输入语音信息。
其中， 本发明实施例中的终端为移动终端或 PC终端。 该移动终端可以为 手机、 PDA ( Personal Digital Assistant, 个人数字助理 )和 MID ( Mobile Internet Devices, 移动互联网设备）等。
步骤 202: 获取当前的环境信息；
该步骤中， 本发明实施例中的当前的环境信息可以为终端自身的硬件信 息， 也可以为用户的操作指令， 也可以为当前的噪声信息等等。 本发明实施例 中对当前的环境信息的具体内容不做限定。
其中， 终端自身的硬件信息包括但不限于终端当前安装的硬件设备信息， 如通过接口连接的音频输入或输出设备， 该硬件信息还可以包括音频输入或输 出设备的驱动信息等等， 如音频编解码器和音频设备驱动等。
用户的操作指令可以是对终端进行的任一操作指令，根据技术人员的开发 时的设置， 不同的操作指令可以对应不同的功能， 如， 对语音信息的点击操作 可以为用于播放该语音信息的操作指令， 而对于语音信息相应的获取文字信息 的选项的点击操作可以为用于获取文字信息的操作指令。
当前的噪声信息是指终端所处环境的噪音信息， 如该终端当前处于会议 室， 则该当前的噪声信息是指该会议室内的噪声信息。 相应地， 获取当前的环 境信息即为获取当前的噪声信息， 该噪声信息可以由终端的麦克风进行， 其具 体过程与获取语音的过程类似， 在此不作赘述。
需要说明的是， 获取的环境信息类型可以由以由技术人员默认设置， 还可 以由用户在使用过程中调整。 对于不同类型的环境信息类型， 其具体的判断过 程不同， 详见步骤 203的描述。
步骤 203: 根据当前的环境信息判断否需要播放语音信息， 若否， 则执行 步骤 204, 若是， 则执行步骤 206;
其中， 语音输入确实能够带给用户更快捷、 更流畅的沟通过程， 但在^艮多 场景下（比如会议室、 嘈杂的环境或对方没有耳机或播放器， 或者语音内容比 较私密等情况下）， 接收方不太方便播放语音。 此时， 为了让接收方顺利的获 知语音发送者要表达的内容， 可以将语音信息识别为文字信息， 便于接收方进 行选择， 接收方可以选择播放语音信息， 也可以选择查看识别后的文字信息。
该步骤中， 根据当前的环境信息的不同， 判断否需要播放语音信息的方式 也不同， 本发明实施例提供下面几种实现方式：
方式一、 当前的环境信息为用户的操作指令；
根据当前的环境信息判断是否需要播放语音信息， 具体包括： 判断该操 作指令是否为获取文字信息的指令， 当该操作指令为获取文字信息的指令时， 则判断出不需要播放语音信息， 执行步骤 204的操作； 当用户的操作指令不是 获取文字信息的指令时， 则判断出需要播放语音信息， 执行步骤 206的操作。
具体地， 用户通过执行操作指令读取终端上接收的语音信息， 该操作指令 可以为点击操作或触摸操作， 本发明在此不做限定。 终端根据用户的操作指令 判断出用户选择哪种获取信息的方式， 其中， 终端接收到用户的操作指令后， 根据该操作指令判断出终端是否需要播放语音信息， 若用户不需要播放语音信 息时， 则需要将该语音信息识别为文字信息并提供给用户； 若用户需要播放语 音信息时， 则终端将该语音信息直接播放给用户即可， 不需要做其他的特殊处 理操作。
例如， 终端上设置至少两个按钮 A和 B , 按钮 A上显示 "语音"、 "喇叭 形状" 等字符， 按钮 B上显示 "文字"、 "ABC" 等字符， 其中， 用户若点击或 触摸按钮 A, 则表明获取到语音信息， 播放出该语音信息； 用户若点击或触摸 按钮 B, 则表明获取到文字信息， 将该文字信息显示出来。
方式二、 当前的环境信息为终端自身的硬件信息；
其中， 终端满足播放语音信息的硬件信息至少包括音频编解码器和音频输 出设备。
根据当前的环境信息判断是否需要播放语音信息， 具体包括： 判断终端自 身的硬件条件是否具备音频解码器和音频输出设备， 当该终端自身的硬件信息 具备音频编解码器和音频输出设备时， 则该终端自身的硬件信息满足播放语音 信息的条件， 此时判断出该终端需要播放语音信息， 执行步骤 206的操作； 当 该终端自身的硬件信息不具备音频编解码器， 或不具备音频输出设备， 或不具 备音频编解码和音频输出设备时， 则该终端自身的硬件信息不满足播放语音信 息的条件， 判断出不需要播放语音信息， 执行步骤 204的操作。
方式三、 当前的环境信息为当前的噪声信息；
本发明预设一定的噪声范围， 如预设的范围为 30分贝至 90分贝， 根据当 前的环境信息判断是否需要播放语音信息， 具体包括： 判断当前的噪声信息是 否在预设的范围内； 当当前的噪声信息在预设的范围内， 则判断出需要播放语 音信息， 执行步骤 206的操作； 当当前的噪声信息不在预设的范围内， 则表明 当前环境为无声环境或特别嘈杂的环境， 判断出不需要播放语音信息， 执行步 骤 204的操作。
其中， 该方式一， 方式二， 方式三为或的关系， 实际应用中， 可以采用方 式一的实现方式， 也可以采用方式二的实现方式， 也可以采用方式三的实现方 式， 也可以设置三种实现方式的优先级， 根据优先级的高低进行实现， 该实现 方式的采用可以由技术人员默认设置， 还可以由用户在使用过程中调整。
步骤 204: 将语音信息识别为文字信息；
具体地， 本发明实施例提供的将获取的语音信息识别为文字信息的方式， 可以在云端进行识别， 也可在本地内置识别模块， 本发明对此不做限制。
其中， 在云端将语音信息识别为文字信息时， 终端将该语音信息发送给云 端的语音识别服务器， 由语音识别服务器进行语音识别， 云端即指网络上， 云 端的语音识别服务器即指网络上的语音识别服务器， 然后语音识别服务器将识 别结果传输给终端，终端接收到该语音识别服务器识别得到的文字信息。其中， 终端将该语音信息传输到网络上指定的语音识别服务器， 该语音识别服务器可 以对一种或多种语音信息进行识别。
其中， 在本地内置识别模块将语音信息识别为文字信息时， 终端将该语音 信息通过终端内置的语音识别模块进行语音识别， 得到文字信息。 其中， 终端 在安装即时通信工具时， 就已经内置了语音识别模块， 终端欲识别该语音信息 时， 直接使用该模块即可对待识别的语音信息进行语音识别， 然后直接将该识 别结果提供给用户即可。
本发明实施例中， 无论是云端识别还是本地内置识别模块， 都需要用到语 音识别技术， 比如： google、 百度、 讯飞等， 本发明实施例对具体采用哪种语 音识别技术不做限定， 只要能将语音信息识别为文字信息即可。
以下将从移动终端和 PC终端两种场景下描述本发明方案。
移动终端场景： 在移动终端的即时通信的聊天场景下， 如图 3所示， 在语 音信息后面， 提供 "文字" 的功能键， 用户点击此键时， 表示用户的操作指令 为获取文字信息的指令， 此时移动终端将语音信息识别成文字信息。
PC终端场景： 在 PC终端的即时通信的聊天场景下， 如图 4所示， 在语音 信息后面， 提供 "识别成文字" 的功能键， 用户点击此键， 表示用户的操作指 令为获取文字信息的指令， 此时 PC终端将该语音信息识别成文字信息。 步骤 205: 将该文字信息显示给用户；
其中， 将语音信息识别为文字信息后， 将该文字信息显示在终端屏幕上。 需要说明的是， 该文字信息在显示时， 可以以独立的信息形式显示在指定 区域， 还可以覆盖在语音信息的显示区域上进行显示， 该原地显示提供更直观 的视觉效果。
步骤 206: 播放该语音信息。
具体地， 终端判断出需要播放语音信息时， 则直接播放该语音信息。
本发明实施例提供的方法， 通过终端接收到即时通信的语音信息时， 为语 音接收方提供语音识别的功能， 以帮助接收方在不方便的情况下正常获知对方 要表达的内容。 例如在公共场合， 不方便播放语音时， 或在无播放设备的情景 下， 无法播放语音时， 用户能够快捷的获知语音内容。 实施例 3
参见图 5 , 本发明实施例提供了一种终端， 所述终端包括：
获取模块 301 , 用于接收用户输入的语音信息；
判断模块 302, 用于获取当前的环境信息， 根据所述当前的环境信息判断 是否需要播放所述语音信息；
识别模块 303 , 用于当判断模块 302的判断结果为否时， 将语音信息识别 文字信息。
其中， 识别模块 303具体包括发送单元和接收单元；
发送单元， 用于当判断模块 302的判断结果为否时， 将语音信息发送给语 音识别服务器， 使语音识别服务器将所述语音信息识别为文字信息；
接收单元， 用于接收语音识别服务器识别得到的文字信息。
其中， 识别模块 303具体包括： 当判断模块 302的判断结果为否时， 将语 音信息通过终端内置的语音识别模块识别为文字信息。
其中， 参见图 6, 判断模块 302具体包括获取单元 3021和判断单元 3022, 获取单元 3021 , 用于获取用户的操作指令；
判断单元 3022,用于当用户的操作指令是获取文字信息的指令时， 则判断 出不需要播放语音信息件； 当用户的操作指令不是获取文字信息的指令时， 则 判断出需要播放语音信息。
其中， 判断模块 302具体包括获取单元 3021和判断单元 3022; 获取单元 3021 , 用于获取终端自身的硬件信息；
判断单元 3022, 用于当终端自身的硬件信息满足播放语音信息的条件时， 则判断出需要播放语音信息； 当终端自身的硬件信息不满足播放语音信息的条 件时， 则判断出不需要播放语音信息。
其中， 判断模块 302具体包括获取单元 3021和判断单元 3022;
获取单元 3021 , 用于获取当前的噪声信息；
判断单元 3022,用于当当前的噪声信息在预设的范围内， 则判断出需要播 放语音信息； 当当前的噪声信息不在预设的范围内， 则判断出不需要播放语音 信息。
其中， 该终端具体为移动终端或 PC终端。 该移动终端可以为手机、 PDA ( Personal Digital Assistant, 个人数字助理 )和 MID ( Mobile Internet Devices , 移动互联网设备）等。
本发明实施例提供的终端， 通过终端接收到即时通信的语音信息时， 为语 音接收方提供语音识别的功能， 以帮助接收方在不方便的情况下正常获知对方 要表达的内容。 例如在公共场合， 不方便播放语音时， 或在无播放设备的情景 下， 无法播放语音时， 用户能够快捷的获知语音内容。
本实施例提供的终端， 具体可以与方法实施例属于同一构思， 其具体实现 过程详见方法实施例， 这里不再赘述。
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。
以上所述仅为本发明的较佳实施例， 并不用以限制本发明， 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， 均应包含在本发明的 保护范围之内。

Claims

权 利 要 求 书
1、 一种即时通信的语音识别方法， 其特征在于， 所述方法包括： 接收用户输入的语音信息；
获取当前的环境信息， 并根据所述当前的环境信息判断是否需要播放所述 语音信息；
判断出不需要播放所述语音信息时， 则将所述语音信息识别为文字信息。
2、 如权利要求 1所述的方法， 其特征在于， 所述将所述语音信息识别为文 字信息， 具体包括：
将所述语音信息发送给云端的语音识别服务器， 使所述语音识别服务器将 所述语音信息识别为文字信息；
接收所述语音识别服务器识别得到的文字信息。
3、 如权利要求 1所述的方法， 其特征在于， 所述将语音信息识别为文字信 息， 具体包括：
将所述语音信息通过终端内置的语音识别模块进行语音识别， 得到文字信 息。
4、 如权利要求 1-3任一权利要求所述的方法， 其特征在于， 所述当前的环 境信息具体为用户的操作指令， 所述根据所述当前的环境信息判断是否需要播 放所述语音信息， 具体包括：
当所述用户的操作指令是获取文字信息的指令时， 则判断出不需要播放所 述语音；
当所述用户的操作指令不是获取文字信息的指令时， 则判断出需要播放所 述语音信息。
5、 如权利要求 1-3任一权利要求所述的方法， 其特征在于， 所述当前的环 境信息具体包括终端自身的硬件信息， 所述根据所述当前的环境信息判断是否 需要播放所述语音信息， 具体包括：
当所述终端自身的硬件信息满足播放所述语音信息的条件时， 则判断出需 要播放所述语音信息；
当所述终端自身的硬件信息不满足播放所述语音信息的条件时， 则判断出 不需要播放所述语音信息。
6、 如权利要求 1-3权利要求所述的方法， 其特征在于， 所述当前的环境信 息具体包括当前的噪声信息， 所述根据所述当前的环境信息判断是否需要播放 所述语音信息， 具体包括：
判断所述当前的噪声信息是否在预设的范围内；
当所述当前的噪声信息在预设的范围内， 则判断出需要播放所述语音信息； 当所述当前的噪声信息不在预设的范围内， 则判断出不需要播放所述语音 信息。
7、 如权利要求 1-3任一权利要求所述的方法， 其特征在于， 所述终端为移 动终端或 PC终端。
8、 一种终端， 其特征在于， 所述终端包括：
获取模块， 用于接收用户输入的语音信息；
判断模块， 用于获取当前的环境信息， 根据所述当前的环境信息判断是否 需要播放所述语音信息；
识别模块， 用于当所述判断模块的判断结果为否时， 将所述语音信息识别 为文字信息。
9、 如权利要求 8所述的终端， 其特征在于， 所述识别模块具体包括发送单 元和接收单元；
所述发送单元， 用于当所述判断模块的判断结果为否时， 将所述语音信息 发送给云端的语音识别服务器， 使所述语音识别服务器将所述语音信息识别为 文字信息；
所述接收单元， 用于接收所述语音识别服务器识别得到的文字信息。
10、 如权利要求 8所述的终端， 其特征在于， 所述识别模块具体包括： 当 所述判断模块的判断结果为否时， 将所述语音信息通过终端内置的语音识别模 块识别为文字信息。
11、 如权利要求 8-10任一权利要求所述的终端， 其特征在于， 所述判断模 块具体包括获取单元和判断单元，
所述获取单元， 用于获取用户的操作指令；
所述判断单元， 用于当所述用户的操作指令是获取文字信息的指令时， 则 判断出不需要播放所述语音信息件； 当所述用户的操作指令不是获取文字信息 的指令时， 则判断出需要播放所述语音信息。
12、 如权利要求 8-10所述的终端， 其特征在于， 所述判断模块具体包括获 取单元和判断单元；
所述获取单元， 用于获取终端自身的硬件信息；
所述判断单元， 用于当所述终端自身的硬件信息满足播放所述语音信息的 条件时， 则判断出需要播放所述语音信息； 当所述终端自身的硬件信息不满足 播放所述语音信息的条件时， 则判断出不需要播放所述语音信息。
13、 如权利要求 8-10所述的终端， 其特征在于， 所述判断模块具体包括获 取单元和判断单元；
所述获取单元， 用于获取当前的噪声信息；
所述判断单元， 用于当所述当前的噪声信息在预设的范围内， 则判断出需 要播放所述语音信息； 当所述当前的噪声信息不在预设的范围内， 则判断出不 需要播放所述语音信息。
14、 如权利要求 8-10任一权利要求所述的终端， 其特征在于， 所述终端为 移动终端或 PC终端。
PCT/CN2013/072086 2012-03-02 2013-03-01 一种即时通信的语音识别方法和终端 WO2013127367A1 (zh)

Priority Applications (3)

Application Number Priority Date Filing Date Title
JP2014559078A JP2015515643A (ja) 2012-03-02 2013-03-01 インスタントコミュニケーション音声認識方法および端末
US14/382,122 US9263029B2 (en) 2012-03-02 2013-03-01 Instant communication voice recognition method and terminal
KR1020147027277A KR101633208B1 (ko) 2012-03-02 2013-03-01 인스턴트 통신 음성 인식 방법 및 단말기

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201210053628.9 2012-03-02
CN2012100536289A CN103295576A (zh) 2012-03-02 2012-03-02 一种即时通信的语音识别方法和终端

Publications (1)

Publication Number Publication Date
WO2013127367A1 true WO2013127367A1 (zh) 2013-09-06

Family

ID=49081658

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2013/072086 WO2013127367A1 (zh) 2012-03-02 2013-03-01 一种即时通信的语音识别方法和终端

Country Status (5)

Country Link
US (1) US9263029B2 (zh)
JP (1) JP2015515643A (zh)
KR (1) KR101633208B1 (zh)
CN (2) CN110164437B (zh)
WO (1) WO2013127367A1 (zh)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2017120960A1 (zh) * 2016-01-17 2017-07-20 段春燕 耳机语音识别功能的数据采集方法以及交流耳机
CN108806682A (zh) * 2018-06-12 2018-11-13 奇瑞汽车股份有限公司 获取天气信息的方法和装置

Families Citing this family (18)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103369477B (zh) 2013-07-02 2016-12-07 华为技术有限公司 显示媒体信息方法、装置、客户端，图形控件显示方法和装置
CN103578474B (zh) * 2013-10-25 2017-09-12 小米科技有限责任公司 一种语音控制方法、装置和设备
CN103632670A (zh) * 2013-11-30 2014-03-12 青岛英特沃克网络科技有限公司 语音和文本消息自动转换系统及其方法
CN103634321B (zh) * 2013-12-04 2017-01-18 百度在线网络技术（北京）有限公司 语音识别结果的展现方法和装置
CN104700836B (zh) * 2013-12-10 2019-01-29 阿里巴巴集团控股有限公司 一种语音识别方法和系统
CN104732975A (zh) * 2013-12-20 2015-06-24 华为技术有限公司 一种语音即时通讯方法及装置
CN103853465A (zh) * 2014-04-01 2014-06-11 湖南科技学院 一种电子教案文字与图片录入方法
CN104184658A (zh) * 2014-09-13 2014-12-03 邹时晨 一种聊天系统
CN104734942B (zh) * 2015-03-13 2018-02-02 日立楼宇技术（广州）有限公司 一种会议管理方法、装置及系统
US9911410B2 (en) * 2015-08-19 2018-03-06 International Business Machines Corporation Adaptation of speech recognition
CN107342088B (zh) * 2017-06-19 2021-05-18 联想(北京)有限公司 一种声音信息的转换方法、装置及设备
CN107483736B (zh) * 2017-08-23 2020-05-15 广东小天才科技有限公司 一种即时通信应用程序的消息处理方法及装置
CN107888479A (zh) * 2017-10-31 2018-04-06 深圳云之家网络有限公司 语音通信方法、装置、计算机设备及存储介质
CN110853662B (zh) * 2018-08-02 2022-06-24 深圳市优必选科技有限公司 语音交互方法、装置及机器人
CN109243447A (zh) * 2018-10-12 2019-01-18 西安蜂语信息科技有限公司 语音发送触发方法及装置
CN110443545A (zh) * 2019-07-18 2019-11-12 深圳市喜悦智慧数据有限公司 一种快递收寄件的数据处理装置和方法
CN110428804A (zh) * 2019-09-04 2019-11-08 广东以诺通讯有限公司 一种智能通信方法及系统
CN112822331B (zh) * 2019-10-30 2023-06-30 阿尔派株式会社 电子装置以及信息输入控制方法

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101079836A (zh) * 2006-12-21 2007-11-28 腾讯科技（深圳）有限公司 一种基于非对称媒体的即时通信方法及系统
CN101098309A (zh) * 2006-06-30 2008-01-02 佛山市顺德区顺达电脑厂有限公司 便携式电子装置与其实时信息服务方法及装置
CN101453611A (zh) * 2007-12-07 2009-06-10 希姆通信息技术（上海）有限公司 失聪者与正常人的视频通讯方法
US20110137660A1 (en) * 2009-12-08 2011-06-09 Skype Limited Encoding and decoding speech signals

Family Cites Families (16)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
IL84948A0 (en) * 1987-12-25 1988-06-30 D S P Group Israel Ltd Noise reduction system
JP2782147B2 (ja) * 1993-03-10 1998-07-30 日本電信電話株式会社 波形編集型音声合成装置
CA2119397C (en) * 1993-03-19 2007-10-02 Kim E.A. Silverman Improved automated voice synthesis employing enhanced prosodic treatment of text, spelling of text and rate of annunciation
JP3450411B2 (ja) * 1994-03-22 2003-09-22 キヤノン株式会社 音声情報処理方法及び装置
US5911129A (en) * 1996-12-13 1999-06-08 Intel Corporation Audio font used for capture and rendering
US6098040A (en) * 1997-11-07 2000-08-01 Nortel Networks Corporation Method and apparatus for providing an improved feature set in speech recognition by performing noise cancellation and background masking
JP2002185569A (ja) * 2000-12-13 2002-06-28 Hitachi Kokusai Electric Inc 携帯端末
JP2004219918A (ja) 2003-01-17 2004-08-05 Canon Inc 音声認識環境判定方法
JP2005078427A (ja) * 2003-09-01 2005-03-24 Hitachi Ltd 携帯端末及びコンピュータ・ソフトウエア
TW200529568A (en) * 2004-01-20 2005-09-01 Koninkl Philips Electronics Nv Enhanced usage of telephones in noisy surroundings
US7551727B2 (en) * 2004-10-20 2009-06-23 Microsoft Corporation Unified messaging architecture
KR100688178B1 (ko) * 2004-12-31 2007-03-02 엘지전자 주식회사 소음인식 통화방법변경 기능이 구비된 이동통신 단말기 및통화방법 변경방법
EP2156652B1 (en) * 2008-02-28 2012-04-25 Leeds, Richard Method and system for notification and telecommunications management
US8638908B2 (en) * 2008-02-28 2014-01-28 Computer Products Introductions, Corp Contextual conversation processing in telecommunication applications
EP2351021B1 (en) * 2008-11-10 2017-09-06 Google, Inc. Determining an operating mode based on the orientation of a mobile device
CN101482976B (zh) * 2009-01-19 2010-10-27 腾讯科技（深圳）有限公司 语音驱动嘴唇形状变化的方法、获取嘴唇动画的方法及装置

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101098309A (zh) * 2006-06-30 2008-01-02 佛山市顺德区顺达电脑厂有限公司 便携式电子装置与其实时信息服务方法及装置
CN101079836A (zh) * 2006-12-21 2007-11-28 腾讯科技（深圳）有限公司 一种基于非对称媒体的即时通信方法及系统
CN101453611A (zh) * 2007-12-07 2009-06-10 希姆通信息技术（上海）有限公司 失聪者与正常人的视频通讯方法
US20110137660A1 (en) * 2009-12-08 2011-06-09 Skype Limited Encoding and decoding speech signals

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2017120960A1 (zh) * 2016-01-17 2017-07-20 段春燕 耳机语音识别功能的数据采集方法以及交流耳机
CN108806682A (zh) * 2018-06-12 2018-11-13 奇瑞汽车股份有限公司 获取天气信息的方法和装置
CN108806682B (zh) * 2018-06-12 2020-12-01 奇瑞汽车股份有限公司 获取天气信息的方法和装置

Also Published As

Publication number Publication date
CN110164437B (zh) 2021-04-16
KR101633208B1 (ko) 2016-06-23
CN103295576A (zh) 2013-09-11
KR20140136964A (ko) 2014-12-01
US9263029B2 (en) 2016-02-16
US20150039298A1 (en) 2015-02-05
JP2015515643A (ja) 2015-05-28
CN110164437A (zh) 2019-08-23

Similar Documents

Publication Publication Date Title
WO2013127367A1 (zh) 一种即时通信的语音识别方法和终端
JP6575658B2 (ja) インタラクティブ・ホワイトボード機器の音声制御
JP6489563B2 (ja) 音量調節方法、システム、デバイス及びプログラム
WO2015085959A1 (zh) 语音处理方法及装置
US9111538B2 (en) Genius button secondary commands
US20180285056A1 (en) Accessory human interface device
WO2018045536A1 (zh) 声音信号处理的方法、终端和耳机
WO2016184295A1 (zh) 即时通讯方法、用户设备及系统
WO2017181615A1 (zh) 一种陌生来电处理方法、装置及移动终端
WO2019071808A1 (zh) 视频画面显示的方法、装置、系统、终端设备及存储介质
JP6904357B2 (ja) 情報処理装置、情報処理方法、及びプログラム
CN103973542B (zh) 一种语音信息处理方法及装置
TW201246899A (en) Handling a voice communication request
WO2022037261A1 (zh) 音频播放、设备管理方法及装置
WO2017101260A1 (zh) 音频切换方法、装置以及存储介质
WO2020063451A1 (zh) 通话留言方法、终端和具有存储功能的装置
WO2016157993A1 (ja) 情報処理装置、情報処理方法およびプログラム
WO2022048020A1 (zh) 蓝牙音箱的控制方法及系统、存储介质及移动终端
WO2020118560A1 (zh) 一种录音方法、装置、电子设备和计算机可读存储介质
WO2022105342A1 (zh) 一种通信连接建立方法、存储介质及设备
WO2018035873A1 (zh) 音频数据处理方法、终端设备和存储介质
CN113808592A (zh) 通话录音的转写方法及装置、电子设备和存储介质
WO2024103926A1 (zh) 语音控制方法、装置、存储介质以及电子设备
JP6927331B2 (ja) 情報処理装置、情報処理方法、およびプログラム
KR100651512B1 (ko) 휴대용 단말기에서 메시지 전송 및 수신방법

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: 13755607

Country of ref document: EP

Kind code of ref document: A1

ENP Entry into the national phase

Ref document number: 2014559078

Country of ref document: JP

Kind code of ref document: A

WWE Wipo information: entry into national phase

Ref document number: 14382122

Country of ref document: US

NENP Non-entry into the national phase

Ref country code: DE

ENP Entry into the national phase

Ref document number: 20147027277

Country of ref document: KR

Kind code of ref document: A

32PN Ep: public notification in the ep bulletin as address of the adressee cannot be established

Free format text: NOTING OF LOSS OF RIGHTS (EPO FORM 1205A DATED 20-01-2015)

122 Ep: pct application non-entry in european phase

Ref document number: 13755607

Country of ref document: EP

Kind code of ref document: A1