公开(公告)号：US20160210968A1

公开(公告)日：2016-07-21

申请号：US14598958

申请日：2015-01-16

申请人： Lisa Ouakil ,  Abdelhamid Ouakil ,  Ouns Mouri ,  Peter Smith

发明人： Lisa Ouakil ,  Abdelhamid Ouakil ,  Ouns Mouri ,  Peter Smith

IPC分类号： G10L15/28 ,  G06F17/27 ,  G10L15/065

CPC分类号： G06F17/274 ,  G06F17/2765 ,  G06F17/2785 ,  G10L15/183 ,  G10L2015/228

摘要： The invention is system and method to recognize speech vocalizations using context-specific grammars and vocabularies. The system and method allow increased accuracy of recognized utterances by eliminating all language encodings irrelevant to the current context and allowing identification of appropriate context transitions. The system and method creates a context dependent speech recognition system with multiple supported contexts, each with specific grammar and vocabulary, and each identifying the potential context transition allowed. The system and method also include programmatic integration between the context dependent speech recognition system and other systems to make use of the recognized speech.

摘要翻译： 本发明是使用上下文特定语法和词汇识别语音发声的系统和方法。 该系统和方法允许通过消除与当前上下文无关的所有语言编码并允许识别适当的上下文转换来增加识别话语的准确性。 系统和方法创建具有多个支持的上下文的上下文相关语音识别系统，每个具有特定语法和词汇，并且每个识别允许的潜在上下文转换。 系统和方法还包括上下文相关语音识别系统与其他系统之间的程序化集成，以利用所识别的语音。

公开(公告)号：US09460721B2

公开(公告)日：2016-10-04

申请号：US14598958

申请日：2015-01-16

申请人： Lisa Ouakil ,  Abdelhamid Ouakil ,  Ouns Mouri ,  Peter Smith

发明人： Lisa Ouakil ,  Abdelhamid Ouakil ,  Ouns Mouri ,  Peter Smith

IPC分类号： G06F17/27 ,  G06F17/20 ,  G10L15/28 ,  G10L15/065

CPC分类号： G06F17/274 ,  G06F17/2765 ,  G06F17/2785 ,  G10L15/183 ,  G10L2015/228

摘要： The invention is system and method to recognize speech vocalizations using context-specific grammars and vocabularies. The system and method allow increased accuracy of recognized utterances by eliminating all language encodings irrelevant to the current context and allowing identification of appropriate context transitions. The system and method creates a context dependent speech recognition system with multiple supported contexts, each with specific grammar and vocabulary, and each identifying the potential context transition allowed. The system and method also include programmatic integration between the context dependent speech recognition system and other systems to make use of the recognized speech.

摘要翻译： 本发明是使用上下文特定语法和词汇识别语音发声的系统和方法。 该系统和方法允许通过消除与当前上下文无关的所有语言编码并允许识别适当的上下文转换来增加识别话语的准确性。 系统和方法创建具有多个支持的上下文的上下文相关语音识别系统，每个具有特定语法和词汇，并且每个识别允许的潜在上下文转换。 系统和方法还包括上下文相关语音识别系统与其他系统之间的程序化集成，以利用所识别的语音。