-
1.
公开(公告)号:US08073681B2
公开(公告)日:2011-12-06
申请号:US11580926
申请日:2006-10-16
申请人: Larry Baldwin , Tom Freeman , Michael Tjalve , Blane Ebersold , Chris Weider
发明人: Larry Baldwin , Tom Freeman , Michael Tjalve , Blane Ebersold , Chris Weider
CPC分类号: G10L15/18 , G06F3/167 , G10L15/183 , G10L15/22 , G10L17/22 , G10L2015/0631
摘要: A cooperative conversational voice user interface is provided. The cooperative conversational voice user interface may build upon short-term and long-term shared knowledge to generate one or more explicit and/or implicit hypotheses about an intent of a user utterance. The hypotheses may be ranked based on varying degrees of certainty, and an adaptive response may be generated for the user. Responses may be worded based on the degrees of certainty and to frame an appropriate domain for a subsequent utterance. In one implementation, misrecognitions may be tolerated, and conversational course may be corrected based on subsequent utterances and/or responses.
摘要翻译: 提供了一种协作会话语音用户界面。 合作对话语音用户界面可以建立在短期和长期共享知识之上,以产生关于用户话语意图的一个或多个显式和/或隐含假设。 可以基于不同程度的确定性对假设进行排序,并且可以为用户生成自适应响应。 响应可以基于确定性的程度来描述,并为后续发音构建适当的域。 在一个实现中,可以容忍误识别,并且可以基于后续话语和/或响应来纠正对话课程。
-
公开(公告)号:US08515765B2
公开(公告)日:2013-08-20
申请号:US13251712
申请日:2011-10-03
申请人: Larry Baldwin , Tom Freeman , Michael Tjalve , Blane Ebersold , Chris Weider
发明人: Larry Baldwin , Tom Freeman , Michael Tjalve , Blane Ebersold , Chris Weider
CPC分类号: G10L15/18 , G06F3/167 , G10L15/183 , G10L15/22 , G10L17/22 , G10L2015/0631
摘要: A cooperative conversational voice user interface is provided. The cooperative conversational voice user interface may build upon short-term and long-term shared knowledge to generate one or more explicit and/or implicit hypotheses about an intent of a user utterance. The hypotheses may be ranked based on varying degrees of certainty, and an adaptive response may be generated for the user. Responses may be worded based on the degrees of certainty and to frame an appropriate domain for a subsequent utterance. In one implementation, misrecognitions may be tolerated, and conversational course may be corrected based on subsequent utterances and/or responses.
-
3.
公开(公告)号:US20120022857A1
公开(公告)日:2012-01-26
申请号:US13251712
申请日:2011-10-03
申请人: Larry BALDWIN , Tom Freeman , Michael Tjalve , Blane Ebersold , Chris Weider
发明人: Larry BALDWIN , Tom Freeman , Michael Tjalve , Blane Ebersold , Chris Weider
IPC分类号: G06F17/27
CPC分类号: G10L15/18 , G06F3/167 , G10L15/183 , G10L15/22 , G10L17/22 , G10L2015/0631
摘要: A cooperative conversational voice user interface is provided. The cooperative conversational voice user interface may build upon short-term and long-term shared knowledge to generate one or more explicit and/or implicit hypotheses about an intent of a user utterance. The hypotheses may be ranked based on varying degrees of certainty, and an adaptive response may be generated for the user. Responses may be worded based on the degrees of certainty and to frame an appropriate domain for a subsequent utterance. In one implementation, misrecognitions may be tolerated, and conversational course may be corrected based on subsequent utterances and/or responses.
摘要翻译: 提供了一种协作会话语音用户界面。 合作对话语音用户界面可以建立在短期和长期共享知识之上,以产生关于用户话语意图的一个或多个显式和/或隐含假设。 可以基于不同程度的确定性对假设进行排序,并且可以为用户生成自适应响应。 响应可以基于确定性的程度来描述,并为后续发音构建适当的域。 在一个实现中,可以容忍误识别,并且可以基于后续话语和/或响应来纠正对话课程。
-
4.
公开(公告)号:US20080091406A1
公开(公告)日:2008-04-17
申请号:US11580926
申请日:2006-10-16
申请人: Larry Baldwin , Tom Freeman , Michael Tjalve , Blane Ebersold , Chris Weider
发明人: Larry Baldwin , Tom Freeman , Michael Tjalve , Blane Ebersold , Chris Weider
IPC分类号: G06F17/28
CPC分类号: G10L15/18 , G06F3/167 , G10L15/183 , G10L15/22 , G10L17/22 , G10L2015/0631
摘要: A cooperative conversational voice user interface is provided. The cooperative conversational voice user interface may build upon short-term and long-term shared knowledge to generate one or more explicit and/or implicit hypotheses about an intent of a user utterance. The hypotheses may be ranked based on varying degrees of certainty, and an adaptive response may be generated for the user. Responses may be worded based on the degrees of certainty and to frame an appropriate domain for a subsequent utterance. In one implementation, misrecognitions may be tolerated, and conversational course may be corrected based on subsequent utterances and/or responses.
摘要翻译: 提供了一种协作会话语音用户界面。 合作对话语音用户界面可以建立在短期和长期共享知识之上,以产生关于用户话语意图的一个或多个显式和/或隐含假设。 可以基于不同程度的确定性对假设进行排序,并且可以为用户生成自适应响应。 响应可以基于确定性的程度来描述,并为后续发音构建适当的域。 在一个实现中,可以容忍误识别,并且可以基于后续话语和/或响应来纠正对话课程。
-
-
-