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

US08478593B2 Enhanced accuracy for speech recognition grammars 有权
标题翻译：增强语音识别语法的准确性
公开(公告)号：US08478593B2
公开(公告)日：2013-07-02
申请号：US13552218
申请日：2012-07-18
申请人： Harry Blanchard , Steven Lewis , Shankarnarayan Sivaprasad , Lan Zhang
发明人： Harry Blanchard , Steven Lewis , Shankarnarayan Sivaprasad , Lan Zhang
IPC分类号： G10L15/18 , G10L15/06 , G10L21/00
CPC分类号： G10L15/19 , G10L15/063 , G10L15/183
摘要： Disclosed herein are methods and systems for recognizing speech. A method embodiment comprises comparing received speech with a precompiled grammar based on a database and if the received speech matches data in the precompiled grammar then returning a result based on the matched data. If the received speech does not match data in the precompiled grammar, then dynamically compiling a new grammar based only on new data added to the database after the compiling of the precompiled grammar. The database may comprise a directory of names.
摘要翻译：这里公开了用于识别语音的方法和系统。方法实施例包括将接收到的语音与基于数据库的预编译语法进行比较，并且如果接收到的语音与预编译语法中的数据匹配，则基于匹配数据返回结果。如果收到的语音与预编译语法中的数据不匹配，则在编译预编译语法之后，仅基于添加到数据库的新数据动态编译新的语法。数据库可以包括名称目录。

2. 发明授权

US07890328B1 Enhanced accuracy for speech recognition grammars 有权
标题翻译：增强语音识别语法的准确性
公开(公告)号：US07890328B1
公开(公告)日：2011-02-15
申请号：US11470685
申请日：2006-09-07
申请人： Harry Blanchard , Steven Lewis , Shankarnarayan Sivaprasad , Lan Zhang
发明人： Harry Blanchard , Steven Lewis , Shankarnarayan Sivaprasad , Lan Zhang
IPC分类号： G10L15/18 , G10L15/06 , G10L21/00
CPC分类号： G10L15/19 , G10L15/063 , G10L15/183
摘要： Disclosed herein are methods and systems for recognizing speech. A method embodiment comprises comparing received speech with a precompiled grammar based on a database and if the received speech matches data in the precompiled grammar then returning a result based on the matched data. If the received speech does not match data in the precompiled grammar, then dynamically compiling a new grammar based only on new data added to the database after the compiling of the precompiled grammar. The database may comprise a directory of names.
摘要翻译：这里公开了用于识别语音的方法和系统。方法实施例包括将接收到的语音与基于数据库的预编译语法进行比较，并且如果接收到的语音与预编译语法中的数据匹配，则基于匹配数据返回结果。如果收到的语音与预编译语法中的数据不匹配，则在编译预编译语法之后，仅基于添加到数据库的新数据动态编译新的语法。数据库可以包括名称目录。

3. 发明授权

US08229746B2 Enhanced accuracy for speech recognition grammars 有权
标题翻译：增强语音识别语法的准确性
公开(公告)号：US08229746B2
公开(公告)日：2012-07-24
申请号：US13026884
申请日：2011-02-14
申请人： Harry Blanchard , Steven Lewis , Shankarnarayan Sivaprasad , Lan Zhang
发明人： Harry Blanchard , Steven Lewis , Shankarnarayan Sivaprasad , Lan Zhang
IPC分类号： G10L15/18 , G10L15/06 , G10L21/00
CPC分类号： G10L15/19 , G10L15/063 , G10L15/183
摘要： Disclosed herein are methods and systems for recognizing speech. A method embodiment comprises comparing received speech with a precompiled grammar based on a database and if the received speech matches data in the precompiled grammar then returning a result based on the matched data. If the received speech does not match data in the precompiled grammar, then dynamically compiling a new grammar based only on new data added to the database after the compiling of the precompiled grammar. The database may comprise a directory of names.
摘要翻译：这里公开了用于识别语音的方法和系统。方法实施例包括将接收到的语音与基于数据库的预编译语法进行比较，并且如果接收到的语音与预编译语法中的数据匹配，则基于匹配数据返回结果。如果收到的语音与预编译语法中的数据不匹配，则在编译预编译语法之后，仅基于添加到数据库的新数据动态编译新的语法。数据库可以包括名称目录。

4. 发明申请

US20110137652A1 ENHANCED ACCURACY FOR SPEECH RECOGNITION GRAMMARS 有权
标题翻译：增强语音识别精度
公开(公告)号：US20110137652A1
公开(公告)日：2011-06-09
申请号：US13026884
申请日：2011-02-14
申请人： Harry Blanchard , Steven Lewis , Shankarnarayan Sivaprasad , Lan Zhang
发明人： Harry Blanchard , Steven Lewis , Shankarnarayan Sivaprasad , Lan Zhang
IPC分类号： G10L15/06
CPC分类号： G10L15/19 , G10L15/063 , G10L15/183
摘要： Disclosed herein are methods and systems for recognizing speech. A method embodiment comprises comparing received speech with a precompiled grammar based on a database and if the received speech matches data in the precompiled grammar then returning a result based on the matched data. If the received speech does not match data in the precompiled grammar, then dynamically compiling a new grammar based only on new data added to the database after the compiling of the precompiled grammar. The database may comprise a directory of names.
摘要翻译：这里公开了用于识别语音的方法和系统。方法实施例包括将接收到的语音与基于数据库的预编译语法进行比较，并且如果接收到的语音与预编译语法中的数据匹配，则基于匹配数据返回结果。如果收到的语音与预编译语法中的数据不匹配，则在编译预编译语法之后，仅基于添加到数据库的新数据动态编译新的语法。数据库可以包括名称目录。

5. 发明申请

US20070280216A1 Method and apparatus for providing a reliable voice extensible markup language service 失效
标题翻译：提供可靠的语音可扩展标记语言服务的方法和装置
公开(公告)号：US20070280216A1
公开(公告)日：2007-12-06
申请号：US11444883
申请日：2006-05-31
申请人： Ricardo Sabat , Shankarnarayan Sivaprasad
发明人： Ricardo Sabat , Shankarnarayan Sivaprasad
IPC分类号： H04L12/66
CPC分类号： H04L65/1053 , H04L65/80 , H04M3/4938 , H04M7/006
摘要： A method and apparatus for providing a reliable Voice Extensible Markup Language (VXML) over packet networks such as Voice over Internet Protocol (VoIP) and Service over Internet Protocol (SoIP) network are disclosed. For example, a service provider may utilize a plurality of content servers that can be accessed by at least one telephony browser. The telephony browser can reach the content browsers directly as well as through a shared server that may load balance among the content servers. When a request for a VXML content, e.g., a VXML application, is received, the telephony browser sends the request to the shared server. If the request fails or a response is not received prior to expiration of a predetermined time interval, then the telephony browser sends a second request directly to one of the content servers that is capable of providing the requested content.
摘要翻译：公开了一种用于通过诸如因特网协议语音（VoIP）和因特网协议服务（SoIP）网络的分组网络提供可靠的语音可扩展标记语言（VXML）的方法和装置。例如，服务提供商可以利用可由至少一个电话浏览器访问的多个内容服务器。电话浏览器可以直接到达内容浏览器，也可以通过可以在内容服务器之间平衡的共享服务器。当接收到对VXML内容（例如VXML应用）的请求时，电话浏览器将该请求发送到共享服务器。如果请求失败或在预定时间间隔期满之前没有接收到响应，则电话浏览器将第二请求直接发送到能够提供所请求的内容的内容服务器之一。

6. 发明授权

US08576712B2 Method and apparatus for providing a reliable voice extensible markup language service 失效
公开(公告)号：US08576712B2
公开(公告)日：2013-11-05
申请号：US11444883
申请日：2006-05-31
申请人： Ricardo Sabat , Shankarnarayan Sivaprasad
发明人： Ricardo Sabat , Shankarnarayan Sivaprasad
IPC分类号： H04L12/66 , H04L12/56 , H04L29/00 , G06F9/455 , H04M7/00 , H04Q7/20 , H04W72/04 , H04W28/08
CPC分类号： H04L65/1053 , H04L65/80 , H04M3/4938 , H04M7/006
摘要： A method and apparatus for providing a reliable Voice Extensible Markup Language (VXML) over packet networks such as Voice over Internet Protocol (VoIP) and Service over Internet Protocol (SoIP) network are disclosed. For example, a service provider may utilize a plurality of content servers that can be accessed by at least one telephony browser. The telephony browser can reach the content browsers directly as well as through a shared server that may load balance among the content servers. When a request for a VXML content, e.g., a VXML application, is received, the telephony browser sends the request to the shared server. If the request fails or a response is not received prior to expiration of a predetermined time interval, then the telephony browser sends a second request directly to one of the content servers that is capable of providing the requested content.

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