专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

1. 发明授权

US08762151B2 Speech recognition for premature enunciation 有权
标题翻译：语音识别过早发音
公开(公告)号：US08762151B2
公开(公告)日：2014-06-24
申请号：US13161872
申请日：2011-06-16
申请人： John J. Correia , Gaurav Talwar , Xufang Zhao , Rathinavelu Chengalvarayan
发明人： John J. Correia , Gaurav Talwar , Xufang Zhao , Rathinavelu Chengalvarayan
IPC分类号： G10L15/04
CPC分类号： G10L15/04 , G10L15/22 , G10L25/78
摘要： Methods of automatic speech recognition for premature enunciation. In one method, a) a user is prompted to input speech, then b) a listening period is initiated to monitor audio via a microphone, such that there is no pause between the end of step a) and the beginning of step b), and then the begin-speaking audible indicator is communicated to the user during the listening period. In another method, a) at least one audio file is played including both a prompt for a user to input speech and a begin-speaking audible indicator to the user, b) a microphone is activated to monitor audio, after playing the prompt but before playing the begin-speaking audible indicator in step a), and c) speech is received from the user via the microphone.
摘要翻译：自动语音识别方法用于过早发音。在一种方法中，a）提示用户输入语音，然后b）启动听觉周期以经由麦克风监视音频，使得步骤a）的结束与步骤b）的开始之间没有暂停，然后在聆听期间将开头的声音指示符传送给用户。在另一种方法中，a）播放至少一个音频文件，包括用户向用户输入语音的提示和开始说话的声音指示符，b）在播放提示之后但是之前激活麦克风来监视音频在步骤a）中播放开头的声音指示符，以及c）通过麦克风从用户接收到语音。

2. 发明申请

US20120150541A1 MALE ACOUSTIC MODEL ADAPTATION BASED ON LANGUAGE-INDEPENDENT FEMALE SPEECH DATA 有权
标题翻译：基于语言独立的女性语音数据的男性声学模型适应
公开(公告)号：US20120150541A1
公开(公告)日：2012-06-14
申请号：US12965508
申请日：2010-12-10
申请人： Gaurav Talwar , Rathinavelu Chengalvarayan
发明人： Gaurav Talwar , Rathinavelu Chengalvarayan
IPC分类号： G10L15/04
CPC分类号： G10L15/065
摘要： A method of generating proxy acoustic models for use in automatic speech recognition includes training acoustic models from speech received via microphone from male speakers of a first language, and adapting the acoustic models in response to language-independent speech data from female speakers of a second language, to generate proxy acoustic models for use during runtime of speech recognition of an utterance from a female speaker of the first language.
摘要翻译：一种用于生成用于自动语音识别的代理声学模型的方法包括：从通过来自第一语言的男性扬声器的麦克风接收的语音训练声学模型，以及响应于来自第二语言的女性说话者的与语言无关的语音数据来适应声学模型，以产生在来自第一语言的女性说话者的话语的语音识别的运行期间使用的代理声学模型。

3. 发明申请

US20130080173A1 CORRECTING UNINTELLIGIBLE SYNTHESIZED SPEECH 有权
标题翻译：纠正不可思议的合成语音
公开(公告)号：US20130080173A1
公开(公告)日：2013-03-28
申请号：US13246131
申请日：2011-09-27
申请人： Gaurav Talwar , Rathinavelu Chengalvarayan
发明人： Gaurav Talwar , Rathinavelu Chengalvarayan
IPC分类号： G10L13/08
CPC分类号： G10L25/69 , G10L13/033
摘要： A method and system of speech synthesis. A text input is received in a text-to-speech system and, using a processor of the system, the text input is processed into synthesized speech which is established as unintelligible. The text input is reprocessed into subsequent synthesized speech and output to a user via a loudspeaker to correct the unintelligible synthesized speech. In one embodiment, the synthesized speech can be established as unintelligible by predicting intelligibility of the synthesized speech, and determining that the predicted intelligibility is lower than a minimum threshold. In another embodiment, the synthesized speech can be established as unintelligible by outputting the synthesized speech to the user via the loudspeaker, and receiving an indication from the user that the synthesized speech is not intelligible.
摘要翻译：语音合成的方法和系统。在文本到语音系统中接收文本输入，并且使用系统的处理器将文本输入处理成合成语音，其被建立为不可理解的。文本输入被重新处理成后续合成语音，并通过扬声器输出给用户以校正无法理解的合成语音。在一个实施例中，通过预测合成语音的可懂度，并且确定预测的可懂度低于最小阈值，可以将合成语音建立为难以理解。在另一实施例中，通过经由扬声器向用户输出合成语音，并且从用户接收到合成语音不可理解的指示，可以将合成语音建立为不可理解。

4. 发明申请

US20120323577A1 SPEECH RECOGNITION FOR PREMATURE ENUNCIATION 有权
标题翻译：语音识别语音识别
公开(公告)号：US20120323577A1
公开(公告)日：2012-12-20
申请号：US13161872
申请日：2011-06-16
申请人： John J. Correia , Rathinavelu Chengalvarayan , Gaurav Talwar , Xufang Zhao
发明人： John J. Correia , Rathinavelu Chengalvarayan , Gaurav Talwar , Xufang Zhao
IPC分类号： G10L15/04 , G10L15/00
CPC分类号： G10L15/04 , G10L15/22 , G10L25/78
摘要： Methods of automatic speech recognition for premature enunciation. In one method, a) a user is prompted to input speech, then b) a listening period is initiated to monitor audio via a microphone, such that there is no pause between the end of step a) and the beginning of step b), and then the begin-speaking audible indicator is communicated to the user during the listening period. In another method, a) at least one audio file is played including both a prompt for a user to input speech and a begin-speaking audible indicator to the user, b) a microphone is activated to monitor audio, after playing the prompt but before playing the begin-speaking audible indicator in step a), and c) speech is received from the user via the microphone.
摘要翻译：自动语音识别方法用于过早发音。在一种方法中，a）提示用户输入语音，然后b）启动听觉周期以经由麦克风监视音频，使得步骤a）的结束与步骤b）的开始之间没有暂停，然后在聆听期间将开头的声音指示符传送给用户。在另一种方法中，a）播放至少一个音频文件，包括用户向用户输入语音的提示和开始说话的声音指示符，b）在播放提示之后但是之前激活麦克风来监视音频在步骤a）中播放开头的声音指示符，以及c）通过麦克风从用户接收到语音。

5. 发明申请

US20120149356A1 METHOD OF INTELLIGENT VEHICLE DIALING 有权
标题翻译：智能车辆拨号方法
公开(公告)号：US20120149356A1
公开(公告)日：2012-06-14
申请号：US12965486
申请日：2010-12-10
申请人： Uma Arun , Rathinavelu Chengalvarayan , Kevin R. Krause , Eray Yasan , Gaurav Talwar , Xufang Zhao , Michael A. Wuergler
发明人： Uma Arun , Rathinavelu Chengalvarayan , Kevin R. Krause , Eray Yasan , Gaurav Talwar , Xufang Zhao , Michael A. Wuergler
IPC分类号： H04M3/00
CPC分类号： H04M3/42178 , H04M1/271 , H04M1/6075 , H04M3/42204 , H04M2203/053
摘要： A method of operating a vehicle telematics unit includes determining the location of a vehicle equipped with a vehicle telematics unit; determining if telematics dialing software operated by the vehicle telematics unit includes a verbal dialing protocol used at the determined vehicle location; if not, identifying one or more verbal dialing protocols used at the determined location of the vehicle; requesting telematics dialing software that includes the one or more identified verbal dialing protocols; receiving the requested telematics dialing software from a central facility; and storing the received telematics dialing software at the vehicle.
摘要翻译：操作车辆远程信息处理单元的方法包括确定配备有车辆远程信息处理单元的车辆的位置; 确定由车辆远程信息处理单元操作的远程通讯业务拨号软件是否包括在所确定的车辆位置处使用的语音拨号协议; 如果不是，则识别在所确定的车辆位置处使用的一个或多个口头拨号协议; 请求包括一个或多个确定的语言拨号协议的远程信息处理拨号软件; 从中央设施接收所请求的远程信息处理拨号软件; 以及将接收到的远程信息处理拨号软件存储在车辆上。

6. 发明申请

US20120109649A1 SPEECH DIALECT CLASSIFICATION FOR AUTOMATIC SPEECH RECOGNITION 审中-公开
标题翻译：用于自动语音识别的语音对话分类
公开(公告)号：US20120109649A1
公开(公告)日：2012-05-03
申请号：US12916962
申请日：2010-11-01
申请人： Gaurav Talwar , Rathinavelu Chengalvarayan
发明人： Gaurav Talwar , Rathinavelu Chengalvarayan
IPC分类号： G10L15/00
CPC分类号： G10L15/005 , G10L15/08
摘要： Automatic speech recognition including receiving speech via a microphone, pre-processing the received speech to generate acoustic feature vectors, classifying dialect of the received speech, selecting at least one of an acoustic model or a lexicon specific to the classified dialect, decoding the acoustic feature vectors using a processor and at least one of the selected dialect-specific acoustic model or selected lexicon to produce a plurality of hypotheses for the received speech, and post-processing the plurality of hypotheses to identify one of the plurality of hypotheses as the received speech.
摘要翻译：自动语音识别，包括通过麦克风接收语音，预处理接收到的语音以产生声学特征向量，对接收到的语音的方言进行分类，选择对分类方言特有的声学模型或词典中的至少一个，解码声学特征使用处理器和所选择的方言特定声学模型或所选词典中的至少一个的矢量来产生用于所接收的语音的多个假设，以及后处理所述多个假设，以将所述多个假设中的一个假定为接收到的语音。

7. 发明申请

US20110010171A1 Singular Value Decomposition for Improved Voice Recognition in Presence of Multi-Talker Background Noise 有权
标题翻译：用于改善多声道背景噪声的语音识别的奇异值分解
公开(公告)号：US20110010171A1
公开(公告)日：2011-01-13
申请号：US12498811
申请日：2009-07-07
申请人： Gaurav Talwar , Rathinavelu Chengalvarayan
发明人： Gaurav Talwar , Rathinavelu Chengalvarayan
IPC分类号： G10L15/20 , G10L17/00
CPC分类号： G10L17/02 , G10L15/20 , G10L2021/02087
摘要： A system and method for providing speech recognition functionality offers improved accuracy and robustness in noisy environments having multiple speakers. The described technique includes receiving speech energy and converting the received speech energy to a digitized form. The digitized speech energy is decomposed into features that are then projected into a feature space having multiple speaker subspaces. The projected features fall either into one of the multiple speaker subspaces or outside of all speaker subspaces. A speech recognition operation is performed on a selected one of the multiple speaker subspaces to resolve the utterance to a command or data.
摘要翻译：用于提供语音识别功能的系统和方法在具有多个扬声器的嘈杂环境中提供改善的精度和鲁棒性。所描述的技术包括接收语音能量并将接收到的语音能量转换成数字化形式。数字化语音能量被分解成特征，然后将其投影到具有多个扬声器子空间的特征空间中。投影的特征落入多个扬声器子空间之一或所有扬声器子空间之外。对多个扬声器子空间中的所选一个执行语音识别操作，以解决对命令或数据的发声。

8. 发明授权

US09564120B2 Speech adaptation in speech synthesis 有权
标题翻译：语音合成中的语音适应
公开(公告)号：US09564120B2
公开(公告)日：2017-02-07
申请号：US12780402
申请日：2010-05-14
申请人： Jeffrey M. Stefan , Gaurav Talwar , Rathinavelu Chengalvarayan
发明人： Jeffrey M. Stefan , Gaurav Talwar , Rathinavelu Chengalvarayan
IPC分类号： G10L13/00 , G10L13/033 , G10L21/013
CPC分类号： G10L13/033 , G10L2021/0135
摘要： A method of and system for speech synthesis. First and second text inputs are received in a text-to-speech system, and processed into respective first and second speech outputs corresponding to stored speech respectively from first and second speakers using a processor of the system. The second speech output of the second speaker is adapted to sound like the first speech output of the first speaker.
摘要翻译：一种用于语音合成的方法和系统。在文本到语音系统中接收第一和第二文本输入，并且使用系统的处理器分别处理分别对应于来自第一和第二扬声器的存储语音的相应的第一和第二语音输出。第二扬声器的第二语音输出适于听起来像第一扬声器的第一语音输出。

9. 发明授权

US09082414B2 Correcting unintelligible synthesized speech 有权
标题翻译：纠正无法理解的合成语音
公开(公告)号：US09082414B2
公开(公告)日：2015-07-14
申请号：US13246131
申请日：2011-09-27
申请人： Gaurav Talwar , Rathinavelu Chengalvarayan
发明人： Gaurav Talwar , Rathinavelu Chengalvarayan
IPC分类号： G10L13/00 , G10L13/08 , G10L15/22 , G10L25/69 , G10L13/033
CPC分类号： G10L25/69 , G10L13/033
摘要： A method and system of speech synthesis. A text input is received in a text-to-speech system and, using a processor of the system, the text input is processed into synthesized speech which is established as unintelligible. The text input is reprocessed into subsequent synthesized speech and output to a user via a loudspeaker to correct the unintelligible synthesized speech. In one embodiment, the synthesized speech can be established as unintelligible by predicting intelligibility of the synthesized speech, and determining that the predicted intelligibility is lower than a minimum threshold. In another embodiment, the synthesized speech can be established as unintelligible by outputting the synthesized speech to the user via the loudspeaker, and receiving an indication from the user that the synthesized speech is not intelligible.
摘要翻译：语音合成的方法和系统。在文本到语音系统中接收文本输入，并且使用系统的处理器将文本输入处理成合成语音，其被建立为不可理解。文本输入被重新处理成后续合成语音，并通过扬声器输出给用户以校正无法理解的合成语音。在一个实施例中，通过预测合成语音的可懂度，并且确定预测的可懂度低于最小阈值，可以将合成语音建立为难以理解。在另一个实施例中，通过经由扬声器向用户输出合成语音，并且从用户接收到合成语音不可理解的指示，可以将合成语音建立为不可理解。

10. 发明授权

US08756062B2 Male acoustic model adaptation based on language-independent female speech data 有权
标题翻译：基于语言无关的女性语音数据的男性声学模型适应
公开(公告)号：US08756062B2
公开(公告)日：2014-06-17
申请号：US12965508
申请日：2010-12-10
申请人： Gaurav Talwar , Rathinavelu Chengalvarayan
发明人： Gaurav Talwar , Rathinavelu Chengalvarayan
IPC分类号： G10L15/00 , G10L15/06 , G10L15/14
CPC分类号： G10L15/065
摘要： A method of generating proxy acoustic models for use in automatic speech recognition includes training acoustic models from speech received via microphone from male speakers of a first language, and adapting the acoustic models in response to language-independent speech data from female speakers of a second language, to generate proxy acoustic models for use during runtime of speech recognition of an utterance from a female speaker of the first language.
摘要翻译：一种用于生成用于自动语音识别的代理声学模型的方法包括：从通过来自第一语言的男性扬声器的麦克风接收的语音训练声学模型，以及响应于来自第二语言的女性说话者的与语言无关的语音数据来适应声学模型，以产生在来自第一语言的女性说话者的话语的语音识别的运行期间使用的代理声学模型。

你已经成功收藏专利！

检索式保存成功!

IPRDB

热门服务

关于我们

友情链接

联系方式