公开(公告)号：US5719921A

公开(公告)日：1998-02-17

申请号：US609029

申请日：1996-02-29

申请人： George J. Vysotsky ,  Ayman O. Asadi ,  David M. Lubensky ,  Vijay R. Raman ,  Jayant M. Naik

发明人： George J. Vysotsky ,  Ayman O. Asadi ,  David M. Lubensky ,  Vijay R. Raman ,  Jayant M. Naik

IPC分类号： G10L15/00 ,  G10L15/06 ,  G10L15/20 ,  G10L15/22 ,  G10L15/26 ,  G10L15/28 ,  H04M3/42 ,  H04M3/44 ,  G10L9/08 ,  H04M1/30 ,  H04M1/66

CPC分类号： H04M1/271 ,  G10L15/065 ,  G10L15/20 ,  G10L15/22 ,  G10L15/26 ,  G10L15/34 ,  H04M3/42204 ,  H04M3/44 ,  G10L2015/088 ,  H04M2201/40 ,  H04M3/42

摘要： Methods and apparatus for activating telephone services in response to speech are described. A directory including names is maintained for each customer. A speaker dependent speech template and a telephone number for each name, is maintained as part of each customer's directory. Speaker independent speech templates are used for recognizing commands. The present invention has the advantage of permitting a customer to place a call by speaking a person's name which serves as a destination identifier without having to speak an additional command or steering word to place the call. This is achieved by treating the receipt of a spoken name in the absence of a command as an implicit command to place a call. Explicit speaker independent commands are used to invoke features or services other than call placement. Speaker independent and speaker dependent speech recognition are performed on a customer's speech in parallel. An arbiter is used to decide which function or service should be performed when an apparent conflict arises as a result of both the speaker dependent and speaker independent speech recognition step outputs. Stochastic grammars, word spotting and/or out-of-vocabulary rejection are used as part of the speech recognition process to provide a user friendly interface which permits the use of spontaneous speech. Voice verification is performed on a selective basis where security is of concern.

摘要翻译： 描述了响应于语音激活电话服务的方法和装置。 为每个客户维护包含名称的目录。 每个名字的说话者依赖语音模板和电话号码都作为每个客户目录的一部分进行维护。 扬声器独立语音模板用于识别命令。 本发明的优点在于，允许客户通过说出作为目的地标识符的人的姓名来进行呼叫，而不用说另外的命令或指导词来进行呼叫。 这是通过在没有命令的情况下处理接收到口语名称作为发出呼叫的隐式命令来实现的。 独立于显示扬声器的命令用于调用除呼叫位置之外的功能或服务。 扬声器独立和扬声器相关语音识别是在客户演讲中并行执行的。 当由于说话人依赖和说话者独立的语音识别步骤输出而产生明显的冲突时，仲裁器用于决定应该执行哪个功能或服务。 语音识别过程的一部分使用随机语法，单词发音和/或超出词汇拒绝，以提供允许使用自发语音的用户友好界面。 语音验证是在安全性受到关注的基础上进行的。

公开(公告)号：US5832063A

公开(公告)日：1998-11-03

申请号：US904920

申请日：1997-08-01

申请人： George J. Vysotsky ,  Ayman O. Asadi ,  David M. Lubensky ,  Vijay R. Raman ,  Jayant M. Naik

发明人： George J. Vysotsky ,  Ayman O. Asadi ,  David M. Lubensky ,  Vijay R. Raman ,  Jayant M. Naik

IPC分类号： G10L15/00 ,  G10L15/06 ,  G10L15/20 ,  G10L15/22 ,  G10L15/26 ,  G10L15/28 ,  H04M3/42 ,  H04M3/44 ,  G10L9/08 ,  H04M1/30 ,  H04M1/66

CPC分类号： H04M1/271 ,  G10L15/065 ,  G10L15/20 ,  G10L15/22 ,  G10L15/26 ,  G10L15/34 ,  H04M3/42204 ,  H04M3/44 ,  G10L2015/088 ,  H04M2201/40 ,  H04M3/42

摘要： Methods and apparatus for activating telephone services in response to speech are described. A directory including names is maintained for each customer. A speaker dependent speech template and a telephone number for each name, is maintained as part of each customer's directory. Speaker independent speech templates are used for recognizing commands. The present invention has the advantage of permitting a customer to place a call by speaking a person's name which serves as a destination identifier without having to speak an additional command or steering word to place the call. This is achieved by treating the receipt of a spoken name in the absence of a command as an implicit command to place a call. Explicit speaker independent commands are used to invoke features or services other than call placement. Speaker independent and speaker dependent speech recognition are performed on a customer's speech in parallel. An arbiter is used to decide which function or service should be performed when an apparent conflict arises as a result of both the speaker dependent and speaker independent speech recognition step outputs. Stochastic grammars, word spotting and/or out-of-vocabulary rejection are used as part of the speech recognition process to provide a user friendly interface which permits the use of spontaneous speech. Voice verification is performed on a selective basis where security is of concern.

公开(公告)号：USRE38101E1

公开(公告)日：2003-04-29

申请号：US09505103

申请日：2000-02-16

申请人： George J. Vysotsky ,  Ayman O. Asadi ,  David M. Lubensky ,  Vijay R. Raman ,  Jayant M. Naik

发明人： George J. Vysotsky ,  Ayman O. Asadi ,  David M. Lubensky ,  Vijay R. Raman ,  Jayant M. Naik

IPC分类号： G10L908

CPC分类号： H04M1/271 ,  G10L15/065 ,  G10L15/20 ,  G10L15/22 ,  G10L15/26 ,  G10L15/34 ,  G10L2015/088 ,  G10L2015/223 ,  H04M3/42 ,  H04M3/42204 ,  H04M3/44 ,  H04M2201/40

摘要： Methods and apparatus for activating telephone services in response to speech are described. A directory including names is maintained for each customer. A speaker dependent speech template and a telephone number for each name, is maintained as part of each customer's directory. Speaker independent speech templates are used for recognizing commands. The present invention has the advantage of permitting a customer to place a call by speaking a person's name which serves as a destination identifier without having to speak an additional command or steering word to place the call. This is achieved by treating the receipt of a spoken name in the absence of a command as an implicit command to place a call. Explicit speaker independent commands are used to invoke features or services other than call placement. Speaker independent and speaker dependent speech recognition are performed on a customer's speech in parallel. An arbiter is used to decide which function or service should be performed when an apparent conflict arises as a result of both the speaker dependent and speaker independent speech recognition step outputs. Stochastic grammars, word spotting and/or out-of-vocabulary rejection are used as part of the speech recognition process to provide a user friendly interface which permits the use of spontaneous speech. Voice verification is performed on a selective basis where security is of concern.

摘要翻译： 描述了响应于语音激活电话服务的方法和装置。 为每个客户维护包含名称的目录。 每个名字的说话者依赖语音模板和电话号码都作为每个客户目录的一部分进行维护。 扬声器独立语音模板用于识别命令。 本发明的优点在于，允许客户通过说出作为目的地标识符的人的姓名来进行呼叫，而不用说另外的命令或指导词来进行呼叫。 这是通过在没有命令的情况下处理接收到口语名称作为发出呼叫的隐式命令来实现的。 独立于显示扬声器的命令用于调用除呼叫位置之外的功能或服务。 扬声器独立和扬声器相关语音识别是在客户演讲中并行执行的。 当由于说话人依赖和说话者独立的语音识别步骤输出而产生明显的冲突时，仲裁器用于决定应该执行哪个功能或服务。 语音识别过程的一部分使用随机语法，单词发音和/或超出词汇拒绝，以提供允许使用自发语音的用户友好界面。 语音验证是在安全性受到关注的基础上进行的。

公开(公告)号：US5842165A

公开(公告)日：1998-11-24

申请号：US846617

申请日：1997-04-30

申请人： Vijay R. Raman ,  George J. Vysotsky

发明人： Vijay R. Raman ,  George J. Vysotsky

IPC分类号： G10L15/00 ,  G10L15/06 ,  G10L15/20 ,  G10L15/22 ,  G10L15/26 ,  G10L15/28 ,  H04M3/42 ,  H04M3/44 ,  G10L9/06

CPC分类号： G10L15/34 ,  G10L15/065 ,  G10L15/20 ,  G10L15/22 ,  G10L15/26 ,  H04M1/271 ,  H04M3/42204 ,  H04M3/44 ,  G10L2015/088 ,  H04M2201/40 ,  H04M3/42

摘要： Methods and apparatus for the generation of speaker dependent garbage models from the very same data used to generate speaker dependent speech recognition models, e.g., word models, are described. The technique involves processing the data included in the speaker dependent speech recognition models to create one or more speaker dependent garbage models. The speaker dependent garbage model generation technique involves what may be described as distorting or morphing of a speaker dependent speech recognition model to generate a speaker dependent garbage model therefrom. One or more speaker dependent speech recognition models may then be combined with the generated speaker dependent garbage model to produce an updated garbage model. The scoring of speaker dependent garbage models is varied in accordance with the present invention as a function of the number of speech recognition models from which the speaker dependent garbage model was created. In one embodiment, the number of speaker dependent speech recognition models which are used in generating a speaker dependent garbage model is limited to a preselected maximum number which is empirically determined.

摘要翻译： 描述了用于从用于产生说话者依赖语音识别模型（例如，字模型）的相同数据生成说话者依赖垃圾模型的方法和装置。 该技术涉及处理包括在说话者依赖语音识别模型中的数据，以创建一个或多个与说话者相关的垃圾模型。 说话者依赖的垃圾模型生成技术涉及可以被描述为说话者依赖语音识别模型的失真或变形以从其产生说话者依赖的垃圾模型。 然后可以将一个或多个与扬声器相关的语音识别模型与所生成的说话者相关的垃圾模型组合以产生更新的垃圾模型。 根据本发明，说话者依赖垃圾模型的评分是根据从其产生说话者依赖的垃圾模型的语音识别模型的数量的函数而变化的。 在一个实施例中，用于产生与说话者有关的垃圾模型的说话者依赖语音识别模型的数量被限制为根据经验确定的预选最大数目。

公开(公告)号：US5895448A

公开(公告)日：1999-04-20

申请号：US846613

申请日：1997-04-30

申请人： George J. Vysotsky ,  Vijay R. Raman

发明人： George J. Vysotsky ,  Vijay R. Raman

IPC分类号： G10L15/00 ,  G10L15/06 ,  G10L15/14 ,  G10L15/20 ,  G10L15/22 ,  G10L15/26 ,  G10L15/28 ,  H04M3/42 ,  H04M3/44 ,  G10L5/00 ,  G10L9/06

CPC分类号： G10L15/34 ,  G10L15/065 ,  G10L15/142 ,  G10L15/20 ,  G10L15/22 ,  G10L15/26 ,  H04M1/271 ,  H04M3/42204 ,  H04M3/44 ,  G10L2015/088 ,  H04M2201/40 ,  H04M3/42

摘要： Methods and apparatus for generating and using both speaker dependent and speaker independent garbage models in speaker dependent speech recognition applications are described. The present invention recognizes that in some speech recognition systems, e.g., systems where multiple speech recognition operations are performed on the same signal, it may be desirable to recognize and treat words or phrases in one part of the speech recognition system as garbage or out of vocabulary utterances with the understanding that the very same words or phrases will be recognized and treated as in-vocabulary by another portion of the system. In accordance with the present invention, in systems where both speaker independent and speaker dependent speech recognition operations are performed independently, e.g., in parallel, one or more speaker independent models of words or phrases which are to be recognized by the speaker independent speech recognizer are included as garbage (OOV) models in the speaker dependent speech recognizer. This reduces the risk of obtaining conflicting speech recognition results from the speaker independent and speaker dependent speech recognition circuits. The present invention also provides for the generation of speaker dependent garbage models from the very same data used to generate speaker dependent speech recognition models, e.g., word models. The technique involves processing the data included in the speaker dependent speech recognition models to create one or more speaker dependent garbage models.

摘要翻译： 描述了依赖于说话者的语音识别应用中的扬声器依赖和扬声器独立垃圾模型的生成和使用的方法和装置。 本发明认识到，在一些语音识别系统中，例如，对相同信号执行多个语音识别操作的系统，可能需要将语音识别系统的一部分中的单词或短语识别和处理为垃圾或从 词汇话语的理解是，相同的单词或短语将被系统的另一部分识别和视为词汇。 根据本发明，在独立地执行独立于说话者和说话者的语音识别操作的系统中，例如并行地执行将由讲话者独立语音识别器识别的一个或多个与说话者无关的单词或短语模型， 在扬声器相关语音识别器中被包括为垃圾（OOV）模型。 这降低了从扬声器独立和扬声器相关语音识别电路获得冲突的语音识别结果的风险。 本发明还提供了从用于产生与扬声器相关的语音识别模型（例如，单词模型）的相同数据生成与扬声器相关的垃圾模型。 该技术涉及处理包括在说话者依赖语音识别模型中的数据，以创建一个或多个与说话者相关的垃圾模型。

公开(公告)号：US6076054A

公开(公告)日：2000-06-13

申请号：US229082

申请日：1999-01-13

申请人： George J. Vysotsky ,  Vijay R. Raman

发明人： George J. Vysotsky ,  Vijay R. Raman

IPC分类号： G10L15/00 ,  G10L15/06 ,  G10L15/14 ,  G10L15/20 ,  G10L15/22 ,  G10L15/26 ,  G10L15/28 ,  H04M3/42 ,  H04M3/44 ,  G10L5/06

CPC分类号： G10L15/34 ,  G10L15/065 ,  G10L15/142 ,  G10L15/20 ,  G10L15/22 ,  G10L15/26 ,  H04M1/271 ,  H04M3/42204 ,  H04M3/44 ,  G10L2015/088 ,  H04M2201/40 ,  H04M3/42

摘要： Methods and apparatus for generating and using both speaker dependent and speaker independent garbage models in speaker dependent speech recognition applications are described. The present invention recognizes that in some speech recognition systems, e.g., systems where multiple speech recognition operations are performed on the same signal, it may be desirable to recognize and treat words or phrases in one part of the speech recognition system as garbage or out of vocabulary utterances with the understanding that the very same words or phrases will be recognized and treated as in-vocabulary by another portion of the system. In accordance with the present invention, in systems where both speaker independent and speaker dependent speech recognition operations are performed independently, e.g., in parallel, one or more speaker independent models of words or phrases which are to be recognized by the speaker independent speech recognizer are included as garbage (OOV) models in the speaker dependent speech recognizer. This reduces the risk of obtaining conflicting speech recognition results from the speaker independent and speaker dependent speech recognition circuits. When an OOV model is recognized, an indication that none of the words represented by the speaker dependent models have been detected may be provided. The present invention also provides for the generation of speaker dependent garbage models from the very same data used to generate speaker dependent speech recognition models, e.g., word models.

摘要翻译： 描述了依赖于说话者的语音识别应用中的扬声器依赖和扬声器独立垃圾模型的生成和使用的方法和装置。 本发明认识到，在一些语音识别系统中，例如，对相同信号执行多个语音识别操作的系统，可能需要将语音识别系统的一部分中的单词或短语识别和处理为垃圾或从 词汇话语的理解是，相同的单词或短语将被系统的另一部分识别和视为词汇。 根据本发明，在独立地执行独立于说话者和说话者的语音识别操作的系统中，例如并行地执行将由讲话者独立语音识别器识别的一个或多个与说话者无关的单词或短语模型， 在扬声器相关语音识别器中被包括为垃圾（OOV）模型。 这降低了从扬声器独立和扬声器相关语音识别电路获得冲突的语音识别结果的风险。 当识别到OOV模型时，可以提供没有检测到由说话者依赖模型表示的词语的指示。 本发明还提供了从用于产生与扬声器相关的语音识别模型（例如，单词模型）的相同数据生成与扬声器相关的垃圾模型。

公开(公告)号：US06229880B1

公开(公告)日：2001-05-08

申请号：US09082553

申请日：1998-05-21

申请人： John R. Reformato ,  George J. Vysotsky

发明人： John R. Reformato ,  George J. Vysotsky

IPC分类号： H04M164

CPC分类号： H04M1/64 ,  H04M3/493 ,  H04M3/533 ,  H04M2201/40

摘要： Methods and apparatus for providing speech recognition capability to callers in a cost efficient manner as part of one or more telephone services are described. Multiple speech recognition units with differing capabilities and therefore implementation costs are provided. Calls are assigned to speech recognition circuits throughout a call based on a signal such as a service type identifier indicating the type of service to be provided to the caller. During different phases of a call different speech recognition units may be used. In addition, different amounts of speech recognition processing capability may be allocated to service a call at different points during a call. In this manner efficient use of available speech recognition resources can be achieved.

摘要翻译： 描述了作为一个或多个电话服务的一部分以成本有效的方式向呼叫者提供语音识别能力的方法和装置。 提供了具有不同功能并因此实现成本的多个语音识别单元。 基于诸如指示要提供给呼叫者的服务类型的服务类型标识符的信号，呼叫在整个呼叫中被分配给语音识别电路。 在呼叫的不同阶段期间，可以使用不同的语音识别单元。 此外，可以分配不同量的语音识别处理能力来在呼叫期间在不同点处服务呼叫。 以这种方式，可以实现有效使用可用的语音识别资源。

公开(公告)号：US06741677B2

公开(公告)日：2004-05-25

申请号：US09850229

申请日：2001-05-07

申请人： John R. Reformato ,  George J. Vysotsky

发明人： John R. Reformato ,  George J. Vysotsky

IPC分类号： H04M164

CPC分类号： H04M1/64 ,  H04M3/493 ,  H04M3/533 ,  H04M2201/40

摘要： Methods and apparatus for providing speech recognition capability to callers in a cost efficient manner as part of one or more telephone services are described. Multiple speech recognition units with differing capabilities and therefore implementation costs are provided. Calls are assigned to speech recognition circuits throughout a call based on a signal such as a service type identifier indicating the type of service to be provided to the caller. During different phases of a call different speech recognition units may be used. In addition, different amounts of speech recognition processing capability may be allocated to service a call at different points during a call. In this manner efficient use of available speech recognition resources can be achieved.

摘要翻译： 描述了作为一个或多个电话服务的一部分以成本有效的方式向呼叫者提供语音识别能力的方法和装置。 提供了具有不同功能并因此实现成本的多个语音识别单元。 基于诸如指示要提供给呼叫者的服务类型的服务类型标识符的信号，呼叫在整个呼叫中被分配给语音识别电路。 在呼叫的不同阶段期间，可以使用不同的语音识别单元。 此外，可以分配不同量的语音识别处理能力来在呼叫期间在不同点处服务呼叫。 以这种方式，可以实现有效使用可用的语音识别资源。