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. 发明专利

AU2013205057A1 Synchronous communication system and method 未知
公开(公告)号：AU2013205057A1
公开(公告)日：2013-10-10
申请号：AU2013205057
申请日：2013-03-22
申请人： GOOGLE INC , LIN JENNIFER W , NAKAJIMA KAISUKE
发明人： LIN JENNIFER W , NAKAJIMA KAISUKE
IPC分类号： H04L29/08
摘要： Abstract A method, computer program product, and computing system for providing a plurality of users of a social network with the ability to indicate affinity with an electronic object. An indication is received from a first user of the plurality of users to initiate an object-specific, synchronous communication session concerning the electronic object. Electronic invitations to join the object-specific, synchronous communication session are provided to one or more invited users of the plurality of users of the social network. A request is received, from at least one of the invited users, to join the object-specific, synchronous communication session. The object-specific, synchronous communication session is provided for the first user and the at least one of the invited users.

2. 发明申请

WO2012148957A3 CROSS-LINGUAL INITIALIZATION OF LANGUAGE MODELS 审中-公开
标题翻译：语言模型的跨语言初始化
公开(公告)号：WO2012148957A3
公开(公告)日：2012-12-20
申请号：PCT/US2012034889
申请日：2012-04-25
申请人： GOOGLE INC , NAKAJIMA KAISUKE , STROPE BRIAN
发明人： NAKAJIMA KAISUKE , STROPE BRIAN
IPC分类号： G10L15/00 , G06F17/28 , G10L15/18
CPC分类号： G10L15/183 , G06F17/289 , G10L15/005 , G10L15/197
摘要： Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for initializing language models for automatic speech recognition. In one aspect, a method includes receiving logged speech recognition results from an existing corpus that is specific to a given language and a target context, generating a target corpus by machine-translating the logged speech recognition results from the given language to a different, target language, and estimating a language model that is specific to the different, target language and the same, target context, using the target corpus.
摘要翻译：包括编码在计算机存储介质上的计算机程序的方法，系统和装置，用于初始化用于自动语音识别的语言模型。在一个方面，一种方法包括从特定于给定语言和目标情境的现有语料库接收记录的语音识别结果，通过将来自给定语言的记录的语音识别结果机器翻译成不同的目标来生成目标语料库语言，并使用目标语料库来估计特定于不同目标语言和相同目标语境的语言模型。

3. 发明申请

WO2012148957A4 CROSS-LINGUAL INITIALIZATION OF LANGUAGE MODELS 审中-公开
标题翻译：语言模型的跨语言初始化
公开(公告)号：WO2012148957A4
公开(公告)日：2013-03-28
申请号：PCT/US2012034889
申请日：2012-04-25
申请人： GOOGLE INC , NAKAJIMA KAISUKE , STROPE BRIAN
发明人： NAKAJIMA KAISUKE , STROPE BRIAN
IPC分类号： G10L15/00 , G06F17/28 , G10L15/18
CPC分类号： G10L15/183 , G06F17/289 , G10L15/005 , G10L15/197
摘要： Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for initializing language models for automatic speech recognition. In one aspect, a method includes receiving logged speech recognition results from an existing corpus that is specific to a given language and a target context, generating a target corpus by machine-translating the logged speech recognition results from the given language to a different, target language, and estimating a language model that is specific to the different, target language and the same, target context, using the target corpus.
摘要翻译：方法，系统和装置，包括在计算机存储介质上编码的计算机程序，用于初始化用于自动语音识别的语言模型。一方面，一种方法包括从特定于给定语言和目标上下文的现有语料库接收记录的语音识别结果，通过将记录的语音识别结果从给定语言机器翻译成不同的目标来产生目标语料库语言，并使用目标语料库估计特定于不同目标语言和相同目标语境的语言模型。

4. 发明申请

WO2013142762A1 SYNCHRONOUS COMMUNICATION SYSTEM AND METHOD 审中-公开
标题翻译：同步通信系统和方法
公开(公告)号：WO2013142762A1
公开(公告)日：2013-09-26
申请号：PCT/US2013/033438
申请日：2013-03-22
申请人： GOOGLE INC. , LIN, Jennifer, W. , NAKAJIMA, Kaisuke
发明人： LIN, Jennifer, W. , NAKAJIMA, Kaisuke
IPC分类号： G06F3/00
CPC分类号： H04L51/32 , G06Q30/0631 , G06Q50/01 , H04L65/403
摘要： A method, computer program product, and computing system for providing a plurality of users of a social network with the ability to indicate affinity with an electronic object. An indication is received from a first user of the plurality of users to initiate an object-specific, synchronous communication session concerning the electronic object. Electronic invitations to join the object-specific, synchronous communication session are provided to one or more invited users of the plurality of users of the social network. A request is received, from at least one of the invited users, to join the object-specific, synchronous communication session. The object-specific, synchronous communication session is provided for the first user and the at least one of the invited users.
摘要翻译：一种用于向社交网络的多个用户提供指示与电子对象的亲和性的能力的方法，计算机程序产品和计算系统。从多个用户的第一用户接收到指示以发起关于电子对象的对象特定的同步通信会话。向对象特定的同步通信会话的电子邀请提供给社交网络的多个用户的一个或多个受邀用户。从至少一个受邀用户接收到加入对象特定的同步通信会话的请求。为第一用户和所邀请的用户中的至少一个提供对象特定的同步通信会话。

5. 发明申请

WO2012148957A2 CROSS-LINGUAL INITIALIZATION OF LANGUAGE MODELS 审中-公开
标题翻译：语言模型的跨语言初始化
公开(公告)号：WO2012148957A2
公开(公告)日：2012-11-01
申请号：PCT/US2012/034889
申请日：2012-04-25
申请人： GOOGLE INC. , NAKAJIMA, Kaisuke , STROPE, Brian
发明人： NAKAJIMA, Kaisuke , STROPE, Brian
IPC分类号： G10L15/00
CPC分类号： G10L15/183 , G06F17/289 , G10L15/005 , G10L15/197
摘要： Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for initializing language models for automatic speech recognition. In one aspect, a method includes receiving logged speech recognition results from an existing corpus that is specific to a given language and a target context, generating a target corpus by machine-translating the logged speech recognition results from the given language to a different, target language, and estimating a language model that is specific to the different, target language and the same, target context, using the target corpus.
摘要翻译：方法，系统和装置，包括在计算机存储介质上编码的计算机程序，用于初始化用于自动语音识别的语言模型。一方面，一种方法包括从特定于给定语言和目标上下文的现有语料库接收记录的语音识别结果，通过将记录的语音识别结果从给定语言机器翻译成不同的目标来产生目标语料库语言，并使用目标语料库估计特定于不同目标语言和相同目标语境的语言模型。

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