New! View global litigation for patent families

CN103839549A - Voice instruction control method and system - Google Patents

Voice instruction control method and system Download PDF

Info

Publication number
CN103839549A
CN103839549A CN 201210478777 CN201210478777A CN103839549A CN 103839549 A CN103839549 A CN 103839549A CN 201210478777 CN201210478777 CN 201210478777 CN 201210478777 A CN201210478777 A CN 201210478777A CN 103839549 A CN103839549 A CN 103839549A
Authority
CN
Grant status
Application
Patent type
Prior art keywords
voice
server
identification
instruction
text
Prior art date
Application number
CN 201210478777
Other languages
Chinese (zh)
Inventor
曾亮
陈磊
薄川川
邓朔
郝宏伟
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

Links

Abstract

The invention discloses a voice instruction control method and system. The voice instruction control method comprises: packing voice data received by a mobile terminal for sending to a server; matching the voice data with training samples in the server, determining a proper identification voice text, and returning the identification voice text to the mobile terminal; and commanding the mobile terminal to execute corresponding operation according to the content of the identification voice text returned by the serer. By using the voice instruction control method and system provided by the invention, the voice data received by the mobile terminal is sent to the server, the server determines the proper identification voice text by matching the voice data with the training samples in the server, such that voice identification is more accurate, the voice instruction accuracy is improved, and the user application experience is improved.

Description

一种语音指令控制方法及系统 A voice control method and system commands

【技术领域】 TECHNICAL FIELD

[0001] 本发明涉及语音控制技术领域,特别涉及一种语音指令控制方法及系统。 [0001] The present invention relates to a voice control technology, and in particular, to a method and system for controlling a voice command.

【背景技术】 【Background technique】

[0002] Siri是iphone4S搭载的一项重要功能,用户可以直接通过语音与智能手机进行简单的交流并对手机发出指令,随着Siri中文版的发布,人们对语音等智能人机交互技术(HCI)的讨论从未终止。 [0002] Siri is an important feature iphone4S equipped user can communicate directly via simple voice phones and smartphones and issue commands, along with the release of the Chinese version of Siri, the voice of the people and other intelligent human-computer interaction (HCI ) discussion never ends. 而Android系统的Voice Actions (语音指令)也提供了非常坚实可靠的声音识别引擎,它的高识别度令人称奇,但要求用户输入的语言具备严格的语法结构和格式,否则系统将无法识别。 The Voice Actions Android system (voice command) also provides a very solid and reliable voice recognition engine, its high degree of recognition amazing, but requires the user to enter a language with strict grammatical structure and format, otherwise the system will not be recognized. 无论iphone的Siri还是Android系统的Voice Actions,都只是基于在移动终端本地进行语音识别,但由于受使用环境或用户发音及语法结构和格式等因素的影响,移动终端会出现语音识别错误或无法识别的情况,影响用户使用体验。 Whether the iphone Siri or Android system, Voice Actions, are only based on speech recognition in a mobile terminal locally, but due to the impact to the environment or user pronunciation and grammar structure and format and other factors, the mobile terminal will speech recognition errors or unrecognized condition that affects the user experience.

[0003] 故,有必要提出一种新的技术方案,以解决现有语音识别技术存在语音识别错误或无法识别的技术问题。 [0003] Therefore, it is necessary to propose a new technical solution to solve technical problems in the existing voice recognition technology of speech recognition errors or unrecognized.

【发明内容】 [SUMMARY]

[0004] 本发明的一个目的在于提供一种语音指令控制方法及系统,旨在解决现有语音识别技术存在语音识别错误或无法识别的技术问题。 [0004] An object of the present invention is to provide a method and a voice command control system designed to solve the technical problems in the prior art speech recognition or speech recognition error unrecognized.

[0005] 为达到上述目的,本发明提供了一种语音指令控制方法,包括: [0005] To achieve the above object, the present invention provides a voice command control method, comprising:

[0006] 将移动终端接收的语音数据打包发送到服务器; [0006] The mobile terminal receives the voice data package sent to the server;

[0007] 将语音数据与服务器中的训练样本进行匹配,确定合适的识别语音文本,并将识别语音文本返回移动终端; [0007] The sample voice data and training matches the server to determine the appropriate text speech recognition, voice recognition and text to return the mobile terminal;

[0008] 根据服务器返回的识别语音文本内容命令移动终端执行对应的操作。 [0008] command corresponding to the mobile terminal performs an operation according to the recognized voice text content returned by the server.

[0009] 在上述语音指令控制方法中,在所述将移动终端接收的语音数据打包发送到服务器步骤前还包括:通过智能语音入口进入智能语音识别界面,等待用户语音输入,并判断在有效时间内是否检测到有效语音输入,如果在有效时间内没有检测到有效语音输入,结束本次语音输入;如果在有效时间内检测到有效语音输入,则接收用户语音。 [0009] In the control method in the voice instruction, the mobile terminal receives the voice data transmitted to the server before the step of packing further comprises: an inlet into the smart voice intelligent voice recognition interface, waits for user's voice input, and determines the effective time detecting whether the valid voice input, if no effective period of time to active speech input, ends the speech input; If a valid voice input within the valid time, the receiving user's voice.

[0010] 在上述语音指令控制方法中,在所述接收用户语音步骤中还包括:判断是否识别到用户语音输入端点或输入超时,如果没有识别到用户语音输入端点或输入没有超时,对接收的语音数据进行编码,并继续接收下一段用户语音;如果识别到用户语音输入端点或输入超时,则停止接收语音数据,完成所有语音数据编码。 [0010] In the control method in the voice instruction, the receiving user speech step further comprises: determining whether the recognized user's speech input terminal or the input timeout, if the user does not recognize the speech input terminal or the input has not timed out, the received voice data encoding, and continues to receive the user's voice period; if the speech recognition to a user input or a timeout input terminal, receiving the voice data is stopped, the completion of all voice data encoding.

[0011] 在上述语音指令控制方法中,在所述将语音数据与服务器中的训练样本进行匹配,确定合适的识别语音文本,并将识别语音文本返回移动终端步骤前还包括:云端服务器接收语音数据编码,将语音数据编码进行解码并去噪处理。 [0011] In the control method of the voice instruction, the voice data with the server matches the training samples, determining appropriate text speech recognition, the recognized speech text and return to the previous step of the mobile terminal further comprises: receiving a voice server Drive data encoding, decoding the encoded voice data and denoising.

[0012] 在上述语音指令控制方法中,在所述将语音数据与服务器中的训练样本进行匹配,确定合适的识别语音文本,并将识别语音文本返回移动终端步骤中还包括:根据语音文本内容附加控制指令。 [0012] In the control method of the voice instruction, the voice data with the server matches the training samples, determining appropriate text speech recognition, voice recognition and text to return the mobile terminal further comprises the step of: the voice text additional control command. [0013] 在上述语音指令控制方法中,在所述根据服务器返回的识别语音文本内容命令移动终端执行对应的操作步骤前还包括:接收识别语音文本并解析控制指令,根据控制指令类型命令移动终端执行语音文本内容对应的操作,其中,所述控制指令类型包括插件应用类型、本地功能类型、热门站点类型及搜索类型。 [0013] In the above-described voice instruction control method, according to the recognized voice text in the content server returns a command corresponding to the mobile terminal before performing further steps comprising: receiving the text and voice recognition analysis control command instructing the mobile terminal according to the control instruction type performing voice text corresponding to an operation, wherein the control instruction types include plug-in application type, the native function type, top site and type of search.

[0014] 本发明还提供了一种语音指令控制系统,包括移动终端和服务器,所述移动终端包括数据发送模块和命令执行模块,所述服务器包括数据匹配模块和数据返回模块, [0014] The present invention also provides a voice command control system including a mobile terminal and a server, the mobile terminal includes a data sending module and a command execution module, the server includes a data matching module and a data return module,

[0015] 数据发送模块:用于将接收的语音数据打包发送到服务器; [0015] Data transmission module: means for receiving voice data package sent to the server;

[0016] 命令执行模块:用于根据服务器返回的识别语音文本内容命令移动终端执行对应的操作; [0016] The command execution module: for the corresponding mobile terminal performs an operation command according to the recognized voice text content returned by the server;

[0017] 数据匹配模块:用于将移动终端发送的语音数据与服务器中的训练样本进行匹配,确定合适的识别语音文本; [0017] Data matching module: for the voice data transmitted from the mobile terminal with the server matches the training samples to determine the appropriate voice recognition text;

[0018] 数据返回模块:用于将识别语音文本返回移动终端。 [0018] The data return module: used to return the recognized voice text mobile terminal.

[0019] 在上述语音指令控制系统中,所述移动终端还包括 [0019] In the voice command control system, the mobile terminal further comprises

[0020] 界面进入模块:用于通过智能语音入口进入智能语音识别界面; [0020] into the interface module: for inlet into the intelligent smart voice speech recognition interface;

[0021] 语音检测模块:用于等待用户语音输入,并判断在有效时间内是否检测到有效语音输入,如果在有效时间内没有检测到有效语音输入,则结束本次语音输入;如果在有效时间内检测到有效语音输入,则通过语音接收模块接收语音数据。 [0021] The speech detection module: waiting for a user's speech input, and determines whether the effective time to detect a valid voice input, if the input is not active speech is detected in the valid time, the end of this speech input; if the effective time the active speech input is detected, the receiving voice data through the voice receiver module.

[0022] 在上述语音指令控制系统中,所述移动终端还包括 [0022] In the voice command control system, the mobile terminal further comprises

[0023] 语音接收模块:用于接收用户语音,并判断是否识别到用户语音输入端点或输入超时,如果没有识别到用户语音输入端点或输入没有超时,则通过数据编码模块对接收的语音数据进行编码,同时语音接收模块继续接收下一段用户语音;如果识别到用户语音输入端点或输入超时,则停止接收语音数据,并通过数据编码模块完成所有语音数据编码; [0023] The voice receiving module: means for receiving a user's voice, and the user determines whether to identify the input speech input terminal or timeout, if the user does not recognize the speech input terminal or the input has not timed out, for the voice data received through the data encoding module encoding, while the receiving module to receive the next voice section voice user; if the speech recognition to a user input or a timeout input terminal, receiving the voice data is stopped, and completing all the speech data encoded by the data encoding module;

[0024] 数据编码模块:用于对接收的所有语音数据进行编码,并通过数据发送模块发送语音数据编码。 [0024] Data encoding module: for all the received encoded voice data, and transmits the encoded voice data via the data transmission module.

[0025] 在上述语音指令控制系统中,所述服务器还包括数据接收模块:用于接收移动终端发送的语音数据编码,将语音数据编码进行解码并去噪处理。 [0025] In the voice command control system, the server further comprises a data receiving module: means for receiving coded voice data sent from the mobile terminal, decoding the encoded voice data and denoising.

[0026] 在上述语音指令控制系统中,所述数据匹配模块还用于在确定合适的识别语音文本后根据语音文本内容附加控制指令。 [0026] In the voice command control system, a data matching module is further configured to upon determining appropriate recognition voice text additional control command according to a voice text.

[0027] 在上述语音指令控制系统中,所述移动终端还包括数据解析模块:用于接收服务器返回的识别语音文本并解析控制指令,所述命令执行模块根据控制指令类型命令移动终端执行语音文本内容对应的操作。 [0027] In the voice command control system, the mobile terminal further comprises a data analysis module: means for recognizing a voice received text returned by the server and parses control commands, the command execution module commands the mobile terminal performs voice text type of control command corresponding to the content of the operation.

[0028] 在上述语音指令控制系统中,所述控制指令类型包括插件应用类型、本地功能类型、热门站点类型及搜索类型。 [0028] In the voice command control system, the control instruction types include plug-in application type, the native function type, top site and type of search.

[0029] 本发明提供的语音指令控制方法及系统将移动终端接收的语音数据发送到服务器,服务器通过将语音数据与服务器中的训练样本进行匹配,确定合适的识别语音文本,使得语音识别更加准确,提高语音指令的精确度,可大大避免移动终端语音识别错误或无法识别的情况,改善用户使用体验;另外,本发明通过识别语音文本内容附加控制指令对移动终端的操作功能进行分类,提高语音指令的精确度。 [0029] The voice command control method and system of the present invention provides the mobile terminal receives the voice data to the server, the server by the speech data matches the training samples server, determining an appropriate recognized speech text, so that the speech recognition more accurate improve the accuracy of voice commands, may be largely avoided where the mobile terminal the speech recognition error or unrecognizable, to improve the user experience; Further, the present invention is the operation of functions of the mobile terminal classifies additional control command by recognizing a voice text content, improving speech precision instruction.

[0030] 为让本发明的上述内容能更明显易懂,下文特举优选实施例,并配合所附图式,作详细说明如下: [0030] In order to make the above-described present invention can be more fully understood, the following preferred non-limiting embodiment, and with the accompanying drawings, described in detail below:

【附图说明】 BRIEF DESCRIPTION

[0031] 图1为本发明第一实施例的语音指令控制方法的流程图; [0031] FIG. 1 is a flowchart of a voice command control method of the first embodiment embodiment of the present invention;

[0032] 图2为本发明第二实施例的语音指令控制方法的流程图; [0032] FIG 2 a second embodiment of a voice command control flowchart of a method of the present invention;

[0033]图3为本发明第一实施例的语音指令控制系统的结构示意图; [0033] Fig 3 a schematic view of the structure of a voice command control system of the first embodiment of the embodiment of the present invention;

[0034]图4为本发明第二实施例的语音指令控制系统的结构示意图。 [0034] FIG. 4 schematic structural diagram of a voice command control system for the second embodiment of the present invention.

【具体实施方式】 【detailed description】

[0035] 以下各实施例的说明是参考附加的图式,用以例示本发明可用以实施的特定实施例。 DESCRIPTION [0035] The following examples are reference to the accompanying drawings for illustrating the embodiments may be used to particular embodiments of the present invention.

[0036] 请参考图1,为本发明第一实施例的语音指令控制方法的流程图。 [0036] Referring to FIG. 1, a flowchart of a voice command control method according to a first embodiment of the embodiment of the present invention. 本发明第一实施例的语音指令控制方法包括下列步骤: The first embodiment of the voice command control method comprising the steps of:

[0037] 步骤SlOO:将移动终端接收的语音数据打包发送到服务器; [0037] Step SlOO: The mobile terminal receives the voice data package sent to the server;

[0038] 步骤SllO:将语音数据与服务器中的训练样本进行匹配,确定合适的识别语音文本,并将识别语音文本返回移动终端; [0038] Step SllO: voice and data server matches the training samples, determining appropriate text speech recognition, voice recognition and text to return the mobile terminal;

[0039] 在步骤SllO中,本发明通过将用户输入的语音数据上传到服务器与服务器中的训练样本进行匹配,使得语音识别更加准确,可大大避免移动终端语音识别错误或无法识别的情况; [0039] In step SllO, the present invention is uploaded by the voice data input by the user to the server and the server training samples are matched, so that more accurate voice recognition, the mobile terminal can be largely avoided or unrecognized speech recognition error situation;

[0040] 步骤S120:根据服务器返回的识别语音文本内容命令移动终端执行对应的操作。 [0040] Step S120: the mobile terminal performs the command corresponding to the operation according to the recognized voice text content returned by the server.

[0041] 请参考图2,为本发明第二实施例的语音指令控制方法的流程图。 [0041] Please refer to FIG 2, a second embodiment of the voice command control flowchart of a method of the present invention. 本发明第二实施例的语音指令控制方法包括下列步骤: The second embodiment of the voice command control method comprising the steps of:

[0042] 步骤S200:通过智能语音入口进入智能语音识别界面; [0042] Step S200: through the inlet into the intelligent intelligent voice speech recognition interface;

[0043] 在步骤S200中,用户可通过点击智能语音快速链接图标或长按toolbar (工具条)一定时间等方式弹出智能语音识别界面,具体请一并参阅图3,是本发明移动终端智能语音识别界面效果图。 [0043] In step S200, the user may click the link icon intelligent speech fast or long press the eject Toolbar (toolbar) a predetermined time intelligent voice recognition interface, etc., particularly Referring to FIG 3, a mobile terminal according to the present invention Intelligent Voice FIG recognition interface effects. 在本发明实施例中,长按toolbar的时间为大于0.5s,具体可根据不同需求进行设置。 In an embodiment of the present invention, a long time is more than toolbar 0.5s, it can be set according to specific needs.

[0044] 步骤S210:等待用户语音输入,并判断在有效时间内是否检测到有效语音输入,如果在有效时间内没有检测到有效语音输入,执行步骤220 ;如果在有效时间内检测到有效语音输入,执行步骤230; [0044] Step S210: waiting for a user voice input, and determines the effective time to detect whether a valid voice input, if no effective period of time to active speech input, step 220; if it is detected valid speech within the valid time input , step 230 is performed;

[0045] 在步骤210中,有效时间是指语音输入的等待时间,可根据不同需求进行设置,在本发明实施例中的有效时间设置为5s ;如果用户在有效时间内输入语音,则为有效语音输入,反之,如果语音输入等待超时,则结束本次输入。 [0045] In step 210, the effective time is the waiting time of the speech input, can be set according to different needs, the effective time is set to 5s embodiment of the present invention, in the embodiment; if the user inputs a voice within the effective time, for the effective voice input, on the contrary, if the voice input waiting timeout, the end of this entry.

[0046] 步骤S220:结束本次语音输入; [0046] Step S220: the end of this speech input;

[0047] 步骤S230:接收用户语音,并判断是否识别到用户语音输入端点或输入超时,如果没有识别到用户语音输入端点或输入没有超时,执行步骤S240 ;如果识别到用户语音输入端点或输入超时,执行步骤250 ; [0047] Step S230: receiving a user voice, and determines whether the recognized user speech input terminal or the input timeout, if no user is identified speech input terminal or the input has not timed out, step S240; if it is recognized user speech input terminal or the input timeout performing step 250;

[0048] 在步骤S230中,识别到用户语音输入端点是指用户输入一个完整的词语或句子后的停顿时间满足端点识别条件,端点识别条件可根据不同情况进行设定,例如5s、10s等;如果识别到用户语音输入端点或输入超时,则默认为本次语音输入完毕,反之,用户可以继续进行语音输入。 [0048] In step S230, the speech recognition user input endpoints of the pause time after the user enters a full word or sentence satisfies endpoint identification condition, node identification conditions can be set according to different circumstances, e.g. 5s, 10s and the like; If the recognized speech input terminal or a user input time out, time-based default voice input is completed, on the contrary, the user can continue the voice input.

[0049] 步骤S240 :对接收的语音数据进行编码,并重新执行步骤S230继续接收下一段用 [0049] Step S240: the received voice data is encoded and re-executes step S230 to receive the next paragraph with

户语音; Households voice;

[0050] 步骤S250 :停止接收语音数据,完成所有语音数据编码; [0050] Step S250: stopping receiving the voice data, the voice data encoding completion of all;

[0051] 步骤S260 :将编码后的所有语音数据打包并通过HTTP请求发送到服务器; [0051] Step S260: All voice data and transmits the encoded package to the server via HTTP request;

[0052] 步骤S270 :云端服务器接收语音数据编码,将语音数据编码进行解码并去噪处理; [0052] Step S270: the server receives the cloud encoded voice data, the voice data encoding and decoding denoising;

[0053] 步骤S280 :将解码后的语音数据与服务器中的训练样本进行匹配,确定合适的识别语音文本,根据语音文本内容附加控制指令; [0053] Step S280: decoding the voice data with the server matches the training samples, determining appropriate text speech recognition, the additional control command according to a voice text;

[0054] 在步骤S280中,本发明通过将用户输入的语音数据上传到服务器与服务器中的训练样本进行匹配,使得语音识别更加准确,可大大避免移动终端语音识别错误或无法识别的情况;控制指令即云端服务器在确定识别语音文本的同时,根据语音文本的具体内容, 将其映射到客户端支持的常用操作上的指令,用户端会根据语音文本的控制指令类型命令移动终端进行对应的操作,例如,播放音乐、发送短信、打电话、打开网页等等,会有一点误识别的情况,但是随着大量用户的使用结果不断修正,该指令也会趋于精确。 [0054] In step S280, the present invention is uploaded by the voice data input by the user to the server with the training sample server match, so that the speech recognition more accurate, can be largely avoided mobile terminal voice recognition error or unrecognized; control instructions on a common operating instructions i.e. the cloud server determines the recognized speech text, while, depending on the content of the speech text, which is mapped to the client supports, the UE would command the mobile terminal to perform a corresponding operation according to a control command voice text type , for example, play music, send text messages, phone calls, open a web page, and so on, without having the slightest mistake will be recognized, but with the large number of users using the result constantly revised, the directive will become accurate.

[0055] 步骤S290 :将语音文本及控制指令返回移动终端; [0055] Step S290: the text, and voice control command to return the mobile terminal;

[0056] 步骤S300 :接收语音文本并解析控制指令,根据控制指令类型命令移动终端执行语音文本内容对应的操作; [0056] Step S300: receiving a voice control commands and parse the text, the type of control command instructs the mobile terminal performs an operation corresponding to the speech text;

[0057] 在步骤S300中,控制指令类型包括插件应用类型、本地功能类型、热门站点类型及搜索类型等,其中,如果控制指令类型为插件应用类型,则根据语音文本内容打开对应的应用,如“音乐插件”、“二维码”等;如果控制指令类型为本地功能类型,则根据语音文本内容调用对应的本地功能,如“打开书签”、“清空所有数据”等;如果控制指令类型为热门站点类型,则根据语音文本内容打开对应的网页,如“腾讯主页”、“新浪网”;不属于上述三种类型的其他语音文本,本发明均认为是搜索类型,直接使用移动终端当前搜索引擎搜索语音文本对应的结果;具体关键数据结构为[0058] typedef enum {[0059] VoiceControlCmdUnkonwn = 0x0,[0060] VoiceControlCmdSerach,[0061] VoiceControlCmdPlugin,[0062] VoiceControlCmdLocalApp,[0063] VoiceControlCmdffebSite[0064] } VoiceControlCmd; //语音控制类型[0 [0057] In step S300, the control instruction types include plug-in application type, the native function type, top site Types of search and the like, wherein, if the control instruction type plug-in application type, open the corresponding application in accordance with the speech text, such as "Music plug-in", "two-dimensional code" and the like; if the type is a local function control instruction type, the contents of the local call in accordance with voice text corresponding to the function, such as "open the bookmark", "clear all data" and the like; if the type is a control command Popular types of sites, open the speech corresponding to the text page, such as "Tencent Home", "News"; not belonging to the other three types of voice text, according to the present invention are believed to be the type of search, the mobile terminal is currently used as search the results engines search the speech corresponding to the text; specific critical data structure [0058] typedef enum {[0059] VoiceControlCmdUnkonwn = 0x0, [0060] VoiceControlCmdSerach, [0061] VoiceControlCmdPlugin, [0062] VoiceControlCmdLocalApp, [0063] VoiceControlCmdffebSite [0064]} VoiceControlCmd ; // voice control type [0 065] typedef struct {[0066] char *text;//语音识别文本[0067] VoiceControlCmd controlCmd; // 控制类型[0068] 请参考图3,为本发明第一实施例的语音指令控制系统的结构示意图。 065] typedef struct {[0066] char * text; // text speech recognition [0067] VoiceControlCmd controlCmd; // control type [0068] Please refer to FIG. 3, a schematic view of the structure of a voice instruction of the first embodiment of a control system of the invention . 本发明第一 The present invention first

实施例的语音指令控制系统包括移动终端和服务器,移动终端包括数据发送模块和命令执行模块,服务器包括数据匹配模块和数据返回模块,其中[0069] 数据发送模块:用于将接收的语音数据打包发送到服务器; Example voice command control system includes a mobile terminal and a server, a mobile terminal includes a data sending module and a command execution module, the server includes a data matching module and a data return module, wherein [0069] the data transmitting module: means for receiving speech data package sent to the server;

[0070] 命令执行模块:用于根据服务器返回的识别语音文本内容命令移动终端执行对应的操作; [0070] The command execution module: for the corresponding mobile terminal performs an operation command according to the recognized voice text content returned by the server;

[0071] 数据匹配模块:用于将移动终端发送的语音数据与服务器中的训练样本进行匹配,确定合适的识别语音文本;其中,本发明通过将用户输入的语音数据上传到服务器与服务器中的训练样本进行匹配,使得语音识别更加准确,可大大避免移动终端语音识别错误或无法识别的情况; [0071] Data matching module: for the voice data transmitted from the mobile terminal with the server matches the training samples to determine the appropriate voice recognition text; wherein the present invention is uploaded to the server by the server the voice data input by the user training samples are matched, so that more accurate voice recognition, the mobile terminal can be largely avoided or unrecognized speech recognition error situation;

[0072] 数据返回模块:用于将识别语音文本返回移动终端; [0072] The data return module: used to return the recognized voice text mobile terminal;

[0073] 请参考图4,为本发明第二实施例的语音指令控制系统的结构示意图。 [0073] Please refer to FIG 4, a voice instruction of the second embodiment of the present invention, a schematic diagram of a control system configuration. 本发明第二实施例的语音指令控制系统包括移动终端和服务器,移动终端包括界面进入模块、语音检测模块、语音接收模块、数据编码模块、数据发送模块、数据解析模块和命令执行模块,服务器包括数据接收模块、数据匹配模块和数据返回模块,其中 Voice command to a second embodiment of the present invention comprises a control system of a mobile terminal and a server, into the mobile terminal includes an interface module, voice detection module, a voice receiving module, a data encoding module, the data transmission module, a data analysis module and a command execution module, the server comprising a data receiving module, a data matching module and a data return module, wherein

[0074] 界面进入模块:用于通过智能语音入口进入智能语音识别界面;其中,用户可通过点击智能语音快速链接图标或长按toolbar (工具条)一定时间等方式弹出智能语音识别界面,具体请一并参阅图3,是本发明移动终端智能语音识别界面效果图。 [0074] into the interface module: intelligent voice recognition interface for entering a smart voice portal; wherein the user can press the pop-up Toolbar intelligent speech recognition interface (toolbar) by clicking on a certain time, etc. Intelligent Voice quick link icon or longer, the request Referring to FIG. 3, the present invention is a mobile intelligent terminal voice recognition interface effects FIG. 在本发明实施例中,长按toolbar的时间为大于0.5s,具体可根据不同需求进行设置。 In an embodiment of the present invention, a long time is more than toolbar 0.5s, it can be set according to specific needs.

[0075] 语音检测模块:用于等待用户语音输入,并判断在有效时间内是否检测到有效语音输入,如果在有效时间内没有检测到有效语音输入,则结束本次语音输入;如果在有效时间内检测到有效语音输入,则通过语音接收模块接收语音数据;其中,有效时间是指语音输入的等待时间,可根据不同需求进行设置,在本发明实施例中的有效时间设置为5s ;如果用户在有效时间内输入语音,则为有效语音输入,反之,如果语音输入等待超时,则结束本次输入。 [0075] The speech detection module: waiting for a user's speech input, and determines whether the effective time to detect a valid voice input, if the input is not active speech is detected in the valid time, the end of this speech input; if the effective time the detection of a valid voice input, the receiving voice data through the voice receiver module; wherein the effective time is the waiting time voice input, can be set according to different needs, the effective time embodiment is set to 5s in the present invention; if the user enter the effective time voice, a voice input was valid, on the contrary, if the voice input waiting timeout, the end of this entry.

[0076] 语音接收模块:用于接收用户语音,并判断是否识别到用户语音输入端点或输入超时,如果没有识别到用户语音输入端点或输入没有超时,则通过数据编码模块对接收的语音数据进行编码,同时语音接收模块继续接收下一段用户语音;如果识别到用户语音输入端点或输入超时,则停止接收语音数据,并通过数据编码模块完成所有语音数据编码;其中,识别到用户语音输入端点是指用户输入一个完整的词语或句子后的停顿时间满足端点识别条件,端点识别条件可根据不同情况进行设定,例如5s、10s等;如果识别到用户语音输入端点或输入超时,则默认为本次语音输入完毕,反之,用户可以继续进行语音输入。 [0076] The voice receiving module: means for receiving a user's voice, and the user determines whether to identify the input speech input terminal or timeout, if the user does not recognize the speech input terminal or the input has not timed out, for the voice data received through the data encoding module encoding, while the voice receiving module to receive the next period of a user's voice; if the recognized user speech input terminal or the input timed out, then stops receiving the voice data, and completing all the speech data encoded by the data encoding module; wherein the recognized user voice input terminal is Dwell time refers to a user input after a complete word or sentence satisfies endpoint identification condition, node identification conditions can be set according to different circumstances, e.g. 5s, 10s and the like; if the recognized speech input terminal or a user input timeout, the default of the present that the voice input is complete, on the contrary, the user can proceed with voice input.

[0077] 数据编码模块:用于对接收的所有语音数据进行编码,并通过数据发送模块发送语音数据编码; [0077] Data encoding module: for all the received encoded voice data, the voice data and transmits the encoded data through the transmission module;

[0078] 数据发送模块:用于将编码后的所有语音数据打包并通过HTTP请求发送到服务器; [0078] The data transmission module: for all voice and coded data package sent to the server by the HTTP request;

[0079] 数据解析模块:用于接收服务器返回的识别语音文本并解析控制指令; [0079] Data analysis module: for recognizing a voice received text returned by the server and analyzing the control command;

[0080] 命令执行模块:用于根据控制指令类型命令移动终端执行语音文本内容对应的操作;其中,控制指令类型包括插件应用类型、本地功能类型、热门站点类型及搜索类型等,其中,如果控制指令类型为插件应用类型,则根据语音文本内容打开对应的应用,如“音乐插件”、“二维码”等;如果控制指令类型为本地功能类型,则根据语音文本内容调用对应的本地功能,如“打开书签”、“清空所有数据”等;如果控制指令类型为热门站点类型,则根据语音文本内容打开对应的网页,如“腾讯主页”、“新浪网”;不属于上述三种类型的其他语音文本,本发明均认为是搜索类型,直接使用移动终端当前搜索引擎搜索语音文本对应的结果;具体关键数据结构为 [0080] The command execution module: for instructing the mobile terminal according to the type of execution control instruction corresponding to the content of the voice text operation; wherein the control instruction types include plug-in application type, the native function type, site type and popular type of search, wherein if the control type of instruction type plug-in application, open a corresponding application, such as "plug-in music", "two-dimensional code" and the like in accordance with voice text contents; if the native function control instruction type is type, the function corresponding to a local call in accordance with voice text content, the "open the bookmark", "clear all data" and the like; if the type of control instruction top site type, the corresponding page is opened, such as "Tencent Home", "News" the voice text; does not belong to the above three types of other voice text, according to the present invention are believed to be the type of search, the search engine directly using the current mobile terminal corresponding to the result of voice text; specific critical data structure

[0081] typedef enum { [0081] typedef enum {

[0082] VoiceControICmdUnkonwn = 0x0, [0082] VoiceControICmdUnkonwn = 0x0,

[0083] VoiceControICmdSerach, [0083] VoiceControICmdSerach,

[0084] VoiceControICmdPlugin, [0084] VoiceControICmdPlugin,

[0085] VoiceControICmdLocalApp, [0085] VoiceControICmdLocalApp,

[0086] VoiceControlCmdffebSite [0086] VoiceControlCmdffebSite

[0087] } VoiceControlCmd; // 语音控制类型 [0087]} VoiceControlCmd; // voice control type

[0088] typedef struct { [0088] typedef struct {

[0089] char *text; //语音识别文本 [0089] char * text; // Text Speech Recognition

[0090] VoiceControlCmd controlCmd;// 控制类型 [0090] VoiceControlCmd controlCmd; // control type

[0091] 数据接收模块:用于接收移动终端发送的语音数据编码,将语音数据编码进行解码并去噪处理; [0091] The data receiving module: means for receiving coded voice data sent from the mobile terminal, decoding the encoded voice data and denoising;

[0092] 数据匹配模块:用于将解码后的语音数据与服务器中的训练样本结果进行匹配,确定合适的识别语音文本,根据语音文本内容附加控制指令;其中,本发明通过将用户输入的语音数据上传到服务器与服务器中的训练样本进行匹配,使得语音识别更加准确,可大大避免移动终端语音识别错误或无法识别的情况;控制指令即云端服务器在确定识别语音文本的同时,根据语音文本的具体内容,将其映射到客户端支持的常用操作上的指令,用户端会根据语音文本的控制指令类型命令移动终端进行对应的操作,例如,播放音乐、发送短信、打电话、打开网页等等,会有一点误识别的情况,但是随着大量用户的使用结果不断修正,该指令也会趋于精确。 [0092] Data matching module: for the speech data and the training sample results server matches the decoded, determine the appropriate text speech recognition, the additional control command according to a voice text content; wherein the present invention is by voice input by the user data uploaded to the server with the training sample server match, so that the speech recognition more accurate, can be largely avoided mobile terminal the speech recognition error or unrecognized case; control commands i.e. a cloud server determines the recognized speech text, while, according to the voice of the text specific operating instructions on a common content, which is mapped to the client supports, the UE would command the control command voice text corresponding to the type of mobile terminal operation, e.g., music, send text messages, phone calls, and so open the page , without having the slightest mistake will be recognized, but with the large number of users using the result constantly revised, the directive will become accurate.

[0093] 数据返回模块:用于将语音文本及控制指令返回移动终端; [0093] The data return module: for text and voice control command to return the mobile terminal;

[0094] 本发明提供的语音指令控制方法及系统将移动终端接收的语音数据发送到服务器,服务器通过将语音数据与服务器中的训练样本进行匹配,确定合适的识别语音文本后再返回移动终端执行对应的操作,使得语音识别更加准确,可大大避免移动终端语音识别错误或无法识别的情况,改善用户使用体验;另外,本发明通过识别语音文本内容附加控制指令对移动终端的操作功能进行分类,提高语音指令的精确度。 [0094] The present invention provides a voice command control method and system for a mobile terminal transmitting received voice data to the server, by matching the speech data server training samples, determining appropriate text speech recognition performed before returning the mobile terminal corresponding to the operation, so that the speech recognition more accurate, can be largely avoided where the mobile terminal the speech recognition error or unrecognizable, to improve the user experience; Further, the present invention is the operation of functions of the mobile terminal classifies additional control command by the recognized speech text, improve the accuracy of the voice instruction.

[0095] 综上所述,虽然本发明已以优选实施例揭露如上,但上述优选实施例并非用以限制本发明,本领域的普通技术人员,在不脱离本发明的精神和范围内,均可作各种更动与润饰,因此本发明的保护范围以权利要求界定的范围为准。 [0095] In summary, although the above disclosed embodiments of the present invention, a preferred, but not the above-described preferred embodiments within the spirit and scope of the invention to limit the present invention, those of ordinary skill in the art, without departing are various changes or modifications may be made, and the scope of the invention defined by the claims in the scope of equivalents.

Claims (13)

  1. 1.一种语音指令控制方法,包括: 将移动终端接收的语音数据打包发送到服务器; 将语音数据与服务器中的训练样本进行匹配,确定合适的识别语音文本,并将识别语音文本返回移动终端; 根据服务器返回的识别语音文本内容命令移动终端执行对应的操作。 A voice command control method comprising: the mobile terminal to receive voice data package sent to the server; the speech data matches the training samples server to determine the appropriate text speech recognition, voice recognition and text to return the mobile terminal ; commanding the mobile terminal performs the corresponding operation according to the recognized voice text content returned by the server.
  2. 2.根据权利要求1所述的语音指令控制方法,其特征在于,在所述将移动终端接收的语音数据打包发送到服务器步骤前还包括:通过智能语音入口进入智能语音识别界面,等待用户语音输入,并判断在有效时间内是否检测到有效语音输入,如果在有效时间内没有检测到有效语音输入,结束本次语音输入;如果在有效时间内检测到有效语音输入,则接收用户语音。 The voice command control according to claim 1, characterized in that the mobile terminal receives the voice data transmitted to the server before the step of packing further comprises: a voice recognition interface by entering the intelligent intelligent voice portal, the user waits for the voice input, and determines whether the effective time to detect a valid voice input, if no effective period of time to active speech input, ends the speech input; If a valid voice input within the valid time, the receiving user's voice.
  3. 3.根据权利要求2所述的语音指令控制方法,其特征在于,在所述接收用户语音步骤中还包括:判断是否识别到用户语音输入端点或输入超时,如果没有识别到用户语音输入端点或输入没有超时,对接收的语音数据进行编码,并继续接收下一段用户语音;如果识别到用户语音输入端点或输入超时,则停止接收语音数据,完成所有语音数据编码。 3. The voice instruction control method according to claim 2, wherein, in the step of receiving user voice further comprises: determining whether the recognized user's speech input terminal or the input timeout, if the user does not recognize the speech input terminal or input has not timed out, the received speech data is encoded, and continues to receive the user's voice period; if the speech recognition to a user input or a timeout input terminal, receiving the voice data is stopped, the completion of all voice data encoding.
  4. 4.根据权利要求3所述的语音指令控制方法,其特征在于,在所述将语音数据与服务器中的训练样本进行匹配,确定合适的识别语音文本,并将识别语音文本返回移动终端步骤前还包括:云端服务器接收语音数据编码,将语音数据编码进行解码并去噪处理。 Before voice instruction according to claim 3, wherein said control method characterized in that the voice data matches the training samples in the server to determine the appropriate text speech recognition, voice recognition and text mobile terminal returns step further comprising: a first server receives the encoded voice data, the voice data encoding and decoding denoising.
  5. 5.根据权利要求1所述的语音指令控制方法,其特征在于,在所述将语音数据与服务器中的训练样本进行匹配,确定合适的识别语音文本,并将识别语音文本返回移动终端步骤中还包括:根据语音文本内容附加控制指令。 The voice instruction according to a control method of claim 1, wherein the voice data matches the training samples in the server to determine the appropriate text speech recognition, voice recognition and text to return the mobile terminal in step further comprising: additional control command in accordance with the speech text.
  6. 6.根据权利要求1或5所述的语音指令控制方法,其特征在于,在所述根据服务器返回的识别语音文本内容命令移动终端执行对应的操作步骤前还包括:接收识别语音文本并解析控制指令,根据控制指令类型命令移动终端执行语音文本内容对应的操作,其中,所述控制指令类型包括插件应用类型、本地功能类型、热门站点类型及搜索类型。 The control method of a voice instruction or claim 5, wherein, in said command according to the recognized voice text content returned by the server corresponding to the mobile terminal before performing further steps comprising: receiving the text and voice recognition analysis control command, the type of control command commanding the mobile terminal performs an operation corresponding to the speech text, wherein said control command comprises a plug-type application type, the native function type, top site and type of search.
  7. 7.一种语音指令控制系统,其特征在于,包括移动终端和服务器,所述移动终端包括数据发送模块和命令执行模块,所述服务器包括数据匹配模块和数据返回模块, 数据发送模块:用于将接收的语音数据打包发送到服务器; 命令执行模块:用于根据服务器返回的识别语音文本内容命令移动终端执行对应的操作; 数据匹配模块:用于将移动终端发送的语音数据与服务器中的训练样本进行匹配,确定合适的识别语音文本; 数据返回模块:用于将识别语音文本返回移动终端。 A voice command control system, comprising a mobile terminal and a server, the mobile terminal includes a data sending module and a command execution module, the server includes a data matching module and a data return module, a data transmission module: for the received voice data package sent to the server; command execution module: for instructing the mobile terminal according to the recognized voice text content returned by the server performs a corresponding operation; data matching module: for training speech data with a server in the mobile terminal transmits samples match, determine the appropriate voice recognition text; data return module: used to return the recognized voice text mobile terminal.
  8. 8.根据权利要求7所述的语音指令控制系统,其特征在于,所述移动终端还包括界面进入模块:用于通过智能语音入口进入智能语音识别界面; 语音检测模块:用于等待用户语音输入,并判断在有效时间内是否检测到有效语音输入,如果在有效时间内没有检测到有效语音输入,则结束本次语音输入;如果在有效时间内检测到有效语音输入,则通过语音接收模块接收语音数据。 Voice instruction according to claim 7, said control system, wherein the mobile terminal further comprises an interface module into the: inlet into a smart voice speech recognition interface smart; speech detection module: waiting for a user's speech input and determines the effective time to detect whether a valid voice input, if no valid speech input within the valid time, the end of this speech input; If a valid voice input within the valid duration, the reception by the voice receiver module voice data.
  9. 9.根据权利要求8所述的语音指令控制系统,其特征在于,所述移动终端还包括语音接收模块:用于接收用户语音,并判断是否识别到用户语音输入端点或输入超时,如果没有识别到用户语音输入端点或输入没有超时,则通过数据编码模块对接收的语音数据进行编码,同时语音接收模块继续接收下一段用户语音;如果识别到用户语音输入端点或输入超时,则停止接收语音数据,并通过数据编码模块完成所有语音数据编码; 数据编码模块:用于对接收的所有语音数据进行编码,并通过数据发送模块发送语音数据编码。 9. The voice command control system of claim 8, wherein the mobile terminal further includes a voice receiving module: means for receiving a user's voice, and the user determines whether to identify the input speech input terminal or timeout, if not identified user speech input terminal or the input has not timed out, then through the data encoding block speech data received encoded, while the voice receiving module to receive the next period of a user's voice; if the recognized user speech input terminal or the input timeout, received speech data is stopped and completing all the speech data encoded by the data encoding module; data encoding module: for all the received encoded voice data, and transmits the encoded voice data via the data transmission module.
  10. 10.根据权利要求9所述的语音指令控制系统,其特征在于,所述服务器还包括数据接收模块:用于接收移动终端发送的语音数据编码,将语音数据编码进行解码并去噪处理。 10. The voice commands the control system according to claim 9, characterized in that said server further comprises a data receiving module: means for receiving coded voice data sent from the mobile terminal, decoding the encoded voice data and denoising.
  11. 11.根据权利要求7所述的语音指令控制系统,其特征在于,所述数据匹配模块还用于在确定合适的识别语音文本后根据语音文本内容附加控制指令。 Voice instruction according to claim 7, said control system, characterized in that the data matching module is further configured to, after determining the appropriate recognized speech text additional control command according to a voice text.
  12. 12.根据权利要求7或11所述的语音指令控制系统,其特征在于,所述移动终端还包括数据解析模块:用于接收服务器返回的识别语音文本并解析控制指令,所述命令执行模块根据控制指令类型命令移动终端执行语音文本内容对应的操作。 Voice instruction according to claim 7 or 11, said control system, wherein the mobile terminal further comprises a data analysis module: means for recognizing a voice received text returned by the server and parses control commands, the command execution module according to type control command commanding the mobile terminal performs an operation corresponding to the speech text.
  13. 13.根据权利要求12所述的语音指令控制系统,其特征在于,所述控制指令类型包括插件应用类型、本地功能类型、热门站点类型及搜索类型。 13. A voice command according to claim 12, wherein the control system, characterized in that said control command includes a plug type application type, the native function type, top site and type of search.
CN 201210478777 2012-11-22 2012-11-22 Voice instruction control method and system CN103839549A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN 201210478777 CN103839549A (en) 2012-11-22 2012-11-22 Voice instruction control method and system

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN 201210478777 CN103839549A (en) 2012-11-22 2012-11-22 Voice instruction control method and system

Publications (1)

Publication Number Publication Date
CN103839549A true true CN103839549A (en) 2014-06-04

Family

ID=50802981

Family Applications (1)

Application Number Title Priority Date Filing Date
CN 201210478777 CN103839549A (en) 2012-11-22 2012-11-22 Voice instruction control method and system

Country Status (1)

Country Link
CN (1) CN103839549A (en)

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104183237A (en) * 2014-09-04 2014-12-03 百度在线网络技术(北京)有限公司 Speech processing method and device for portable terminal
CN104268195A (en) * 2014-09-19 2015-01-07 三星电子(中国)研发中心 Method and device for processing local resources in terminal
CN105094807A (en) * 2015-06-25 2015-11-25 三星电子(中国)研发中心 Method and device for implementing voice control
WO2016112634A1 (en) * 2015-01-12 2016-07-21 芋头科技(杭州)有限公司 Voice recognition system and method of robot system

Citations (20)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20020193998A1 (en) * 2001-05-31 2002-12-19 Dvorak Joseph L. Virtual speech interface system and method of using same
CN1627672A (en) * 2003-05-02 2005-06-15 索尼株式会社 Network system, electronic equipment terminal, server apparatus and method for distributing and reproducing the contents
KR20060034337A (en) * 2004-10-18 2006-04-24 주식회사 팬택 Mobile phone and server for managing home-network by voice, and system and method for home-network management using the same
CN101360118A (en) * 2007-08-02 2009-02-04 广东新支点技术服务有限公司 Method and protocol suitable for mobile terminal multimedia file sharing and searching
CN101437039A (en) * 2007-11-15 2009-05-20 华为技术有限公司 Mobile searching method, system and equipment
CN101599270A (en) * 2008-06-02 2009-12-09 海尔集团公司;青岛海尔智能家电科技有限公司 Voice server and voice control method
US20100088100A1 (en) * 2008-10-02 2010-04-08 Lindahl Aram M Electronic devices with voice command and contextual data processing capabilities
CN102270213A (en) * 2011-04-20 2011-12-07 深圳市凯立德科技股份有限公司 The method of searching a point of interest in navigation systems, the terminal device and the service location
CN102316162A (en) * 2011-09-01 2012-01-11 深圳市子栋科技有限公司 Vehicle remote control method based on voice command, apparatus and system thereof
CN102316361A (en) * 2011-07-04 2012-01-11 深圳市子栋科技有限公司 Audio-frequency / video-frequency on demand method based on natural speech recognition and system thereof
US20120030712A1 (en) * 2010-08-02 2012-02-02 At&T Intellectual Property I, L.P. Network-integrated remote control with voice activation
CN102497391A (en) * 2011-11-21 2012-06-13 宇龙计算机通信科技(深圳)有限公司 Server, mobile terminal and prompt method
CN102497481A (en) * 2011-12-02 2012-06-13 深圳市车音网科技有限公司 Method, device and system for voice dialing
CN102541505A (en) * 2011-01-04 2012-07-04 中国移动通信集团公司 Voice input method and system thereof
CN102571882A (en) * 2010-12-31 2012-07-11 上海博泰悦臻电子设备制造有限公司 Network-based voice reminding method and system
CN102629246A (en) * 2012-02-10 2012-08-08 北京百纳信息技术有限公司 Server used for recognizing browser voice commands and browser voice command recognition system
CN102724309A (en) * 2012-06-14 2012-10-10 广东好帮手电子科技股份有限公司 Vehicular voice network music system and control method thereof
CN102741146A (en) * 2010-02-23 2012-10-17 三菱电机株式会社 Elevator device
CN102760431A (en) * 2012-07-12 2012-10-31 上海语联信息技术有限公司 Intelligentized voice recognition system
CN102792320A (en) * 2010-01-18 2012-11-21 苹果公司 Intelligent automated assistant

Patent Citations (20)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20020193998A1 (en) * 2001-05-31 2002-12-19 Dvorak Joseph L. Virtual speech interface system and method of using same
CN1627672A (en) * 2003-05-02 2005-06-15 索尼株式会社 Network system, electronic equipment terminal, server apparatus and method for distributing and reproducing the contents
KR20060034337A (en) * 2004-10-18 2006-04-24 주식회사 팬택 Mobile phone and server for managing home-network by voice, and system and method for home-network management using the same
CN101360118A (en) * 2007-08-02 2009-02-04 广东新支点技术服务有限公司 Method and protocol suitable for mobile terminal multimedia file sharing and searching
CN101437039A (en) * 2007-11-15 2009-05-20 华为技术有限公司 Mobile searching method, system and equipment
CN101599270A (en) * 2008-06-02 2009-12-09 海尔集团公司;青岛海尔智能家电科技有限公司 Voice server and voice control method
US20100088100A1 (en) * 2008-10-02 2010-04-08 Lindahl Aram M Electronic devices with voice command and contextual data processing capabilities
CN102792320A (en) * 2010-01-18 2012-11-21 苹果公司 Intelligent automated assistant
CN102741146A (en) * 2010-02-23 2012-10-17 三菱电机株式会社 Elevator device
US20120030712A1 (en) * 2010-08-02 2012-02-02 At&T Intellectual Property I, L.P. Network-integrated remote control with voice activation
CN102571882A (en) * 2010-12-31 2012-07-11 上海博泰悦臻电子设备制造有限公司 Network-based voice reminding method and system
CN102541505A (en) * 2011-01-04 2012-07-04 中国移动通信集团公司 Voice input method and system thereof
CN102270213A (en) * 2011-04-20 2011-12-07 深圳市凯立德科技股份有限公司 The method of searching a point of interest in navigation systems, the terminal device and the service location
CN102316361A (en) * 2011-07-04 2012-01-11 深圳市子栋科技有限公司 Audio-frequency / video-frequency on demand method based on natural speech recognition and system thereof
CN102316162A (en) * 2011-09-01 2012-01-11 深圳市子栋科技有限公司 Vehicle remote control method based on voice command, apparatus and system thereof
CN102497391A (en) * 2011-11-21 2012-06-13 宇龙计算机通信科技(深圳)有限公司 Server, mobile terminal and prompt method
CN102497481A (en) * 2011-12-02 2012-06-13 深圳市车音网科技有限公司 Method, device and system for voice dialing
CN102629246A (en) * 2012-02-10 2012-08-08 北京百纳信息技术有限公司 Server used for recognizing browser voice commands and browser voice command recognition system
CN102724309A (en) * 2012-06-14 2012-10-10 广东好帮手电子科技股份有限公司 Vehicular voice network music system and control method thereof
CN102760431A (en) * 2012-07-12 2012-10-31 上海语联信息技术有限公司 Intelligentized voice recognition system

Cited By (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104183237A (en) * 2014-09-04 2014-12-03 百度在线网络技术(北京)有限公司 Speech processing method and device for portable terminal
CN104183237B (en) * 2014-09-04 2017-10-31 百度在线网络技术(北京)有限公司 Voice processing method and apparatus for a portable terminal,
CN104268195A (en) * 2014-09-19 2015-01-07 三星电子(中国)研发中心 Method and device for processing local resources in terminal
WO2016112634A1 (en) * 2015-01-12 2016-07-21 芋头科技(杭州)有限公司 Voice recognition system and method of robot system
CN105094807A (en) * 2015-06-25 2015-11-25 三星电子(中国)研发中心 Method and device for implementing voice control

Similar Documents

Publication Publication Date Title
US7873523B2 (en) Computer implemented method of analyzing recognition results between a user and an interactive application utilizing inferred values instead of transcribed speech
US20090299745A1 (en) System and method for an integrated, multi-modal, multi-device natural language voice services environment
US20030217161A1 (en) Method and system for multi-modal communication
US20110110502A1 (en) Real time automatic caller speech profiling
US20100241431A1 (en) System and Method for Multi-Modal Input Synchronization and Disambiguation
US20110055256A1 (en) Multiple web-based content category searching in mobile search application
US20110054894A1 (en) Speech recognition through the collection of contact information in mobile dictation application
US20110054900A1 (en) Hybrid command and control between resident and remote speech recognition facilities in a mobile voice-to-speech application
Schalkwyk et al. “Your word is my command”: Google search by voice: a case study
US20130219277A1 (en) Gesture and Voice Controlled Browser
US20130151250A1 (en) Hybrid speech recognition
US20120271631A1 (en) Speech recognition using multiple language models
US20120179471A1 (en) Configurable speech recognition system using multiple recognizers
US8635243B2 (en) Sending a communications header with voice recording to send metadata for use in speech recognition, formatting, and search mobile search application
US20130332164A1 (en) Name recognition system
US8606581B1 (en) Multi-pass speech recognition
CN102629246A (en) Server used for recognizing browser voice commands and browser voice command recognition system
US20160042748A1 (en) Voice application architecture
US9305548B2 (en) System and method for an integrated, multi-modal, multi-device natural language voice services environment
US20040143436A1 (en) Apparatus and method of processing natural language speech data
US20140358516A1 (en) Real-time, bi-directional translation
US9437186B1 (en) Enhanced endpoint detection for speech recognition
US20150170641A1 (en) System and method for providing a natural language content dedication service
US20110166855A1 (en) Systems and Methods for Hands-free Voice Control and Voice Search
US20130085753A1 (en) Hybrid Client/Server Speech Recognition In A Mobile Device

Legal Events

Date Code Title Description
C06 Publication
C10 Entry into substantive examination