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

US08626511B2 Multi-dimensional disambiguation of voice commands 有权
标题翻译：语音命令的多维消歧
公开(公告)号：US08626511B2
公开(公告)日：2014-01-07
申请号：US12692307
申请日：2010-01-22
申请人： Michael J. LeBeau , William J. Byrne , Nicholas Jitkoff , Alexander H. Gruenstein
发明人： Michael J. LeBeau , William J. Byrne , Nicholas Jitkoff , Alexander H. Gruenstein
IPC分类号： G10L21/00
CPC分类号： G10L15/30
摘要： Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for processing voice commands. In one aspect, a method includes receiving an audio signal at a server, performing, by the server, speech recognition on the audio signal to identify one or more candidate terms that match one or more portions of the audio signal, identifying one or more possible intended actions for each candidate term, providing information for display on a client device, the information specifying the candidate terms and the actions for each candidate term, receiving from the client device an indication of an action selected by a user, where the action was selected from among the actions included in the provided information, and invoking the action selected by the user.
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用于处理语音命令的计算机程序。在一个方面，一种方法包括在服务器处接收音频信号，由服务器执行音频信号上的语音识别以识别与音频信号的一个或多个部分相匹配的一个或多个候选项，识别一个或多个可能的针对每个候选项的预期动作，提供用于在客户端设备上显示的信息，指定候选项的信息和每个候选项的动作，从客户端设备接收由用户选择的动作的指示，其中选择了动作从提供的信息中包括的动作中，并且调用用户选择的动作。

2. 发明申请

US20110184730A1 MULTI-DIMENSIONAL DISAMBIGUATION OF VOICE COMMANDS 有权
标题翻译：语音指令的多维度排除
公开(公告)号：US20110184730A1
公开(公告)日：2011-07-28
申请号：US12692307
申请日：2010-01-22
申请人： Michael J. LeBeau , William J. Byrne , Nicholas Jitkoff , Alexander H. Gruenstein
发明人： Michael J. LeBeau , William J. Byrne , Nicholas Jitkoff , Alexander H. Gruenstein
IPC分类号： G10L21/00 , G10L15/26
CPC分类号： G10L15/30
摘要： Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for processing voice commands. In one aspect, a method includes receiving an audio signal at a server, performing, by the server, speech recognition on the audio signal to identify one or more candidate terms that match one or more portions of the audio signal, identifying one or more possible intended actions for each candidate term, providing information for display on a client device, the information specifying the candidate terms and the actions for each candidate term, receiving from the client device an indication of an action selected by a user, where the action was selected from among the actions included in the provided information, and invoking the action selected by the user.
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用于处理语音命令的计算机程序。在一个方面，一种方法包括在服务器处接收音频信号，由服务器执行音频信号上的语音识别以识别与音频信号的一个或多个部分相匹配的一个或多个候选项，识别一个或多个可能的针对每个候选项的预期动作，提供用于在客户端设备上显示的信息，指定候选项的信息和每个候选项的动作，从客户端设备接收由用户选择的动作的指示，其中选择了动作从提供的信息中包括的动作中，并且调用用户选择的动作。

3. 发明申请

US20110246944A1 APPLICATION-INDEPENDENT TEXT ENTRY 审中-公开
标题翻译：应用独立文本输入
公开(公告)号：US20110246944A1
公开(公告)日：2011-10-06
申请号：US12754883
申请日：2010-04-06
申请人： William J. Byrne , Brett Rolston Lider , Nicholas Jitkoff , Alexander H. Gruenstein , Benedict Davies
发明人： William J. Byrne , Brett Rolston Lider , Nicholas Jitkoff , Alexander H. Gruenstein , Benedict Davies
IPC分类号： G06F3/048
CPC分类号： G06F3/0489 , G06F3/04895 , G06F9/451 , G06F9/543 , G06Q10/107 , G06Q10/109
摘要： A text processing module can allow a user to compose text prior to selecting another application with which to use or communicate the text. A device can include the text processing module, which receives text input from a user via text input means. The device can display the text in a user interface, along with one or more icons associated with software applications with which the text can be used or communicated. After the user has entered text, the user can activate a displayed icon to select the applications. The text processing module receives the selection and interacts with the selected application to display the text in the selected application and/or communicate the text to another person using the selected application. The text processing module can interact with user contacts to identify possible recipients for the text based on information in the text.
摘要翻译：文本处理模块可以允许用户在选择用于或传达文本的另一应用之前撰写文本。设备可以包括文本处理模块，其经由文本输入装置从用户接收文本输入。设备可以在用户界面中显示文本，以及与可以使用或传达文本的软件应用相关联的一个或多个图标。用户输入文本后，用户可以激活显示的图标来选择应用程序。文本处理模块接收选择并与所选择的应用进行交互以在所选择的应用中显示文本和/或使用所选择的应用将文本传送给另一人。文本处理模块可以与用户联系人进行交互，以基于文本中的信息识别文本的可能接收者。

4. 发明授权

US08738377B2 Predicting and learning carrier phrases for speech input 有权
标题翻译：预测和学习语音输入的载波短语
公开(公告)号：US08738377B2
公开(公告)日：2014-05-27
申请号：US12795257
申请日：2010-06-07
申请人： William J. Byrne , Alexander H. Gruenstein , Douglas Beeferman
发明人： William J. Byrne , Alexander H. Gruenstein , Douglas Beeferman
IPC分类号： G10L15/04
CPC分类号： G10L15/22 , G06F3/04842 , G06F3/167 , G06F17/2795 , G10L15/02 , G10L15/063 , G10L15/1822 , G10L15/26 , G10L2015/0631 , G10L2015/0635 , G10L2015/0638 , G10L2015/221
摘要： Predicting and learning users' intended actions on an electronic device based on free-form speech input. Users' actions can be monitored to develop of a list of carrier phrases having one or more actions that correspond to the carrier phrases. A user can speak a command into a device to initiate an action. The spoken command can be parsed and compared to a list of carrier phrases. If the spoken command matches one of the known carrier phrases, the corresponding action(s) can be presented to the user for selection. If the spoken command does not match one of the known carrier phrases, search results (e.g., Internet search results) corresponding to the spoken command can be presented to the user. The actions of the user in response to the presented action(s) and/or the search results can be monitored to update the list of carrier phrases.
摘要翻译：基于自由形式语音输入，预测和学习用户对电子设备的预期动作。可以监视用户的动作，以开发具有与运营商短语对应的一个或多个动作的运营商短语列表。用户可以向设备发出命令以启动动作。可以解析口头命令并将其与载体短语列表进行比较。如果口头命令与已知的运营商短语之一匹配，则可以将相应的动作呈现给用户进行选择。如果口头命令与已知的运营商短语之一不匹配，则可以向用户呈现与口语命令相对应的搜索结果（例如，因特网搜索结果）。可以监视用户响应于所呈现的动作和/或搜索结果的动作以更新运营商短语列表。

5. 发明申请

US20110301955A1 Predicting and Learning Carrier Phrases for Speech Input 有权
标题翻译：预测和学习语音输入的载波短语
公开(公告)号：US20110301955A1
公开(公告)日：2011-12-08
申请号：US12795257
申请日：2010-06-07
申请人： William J. Byrne , Alexander H. Gruenstein , Douglas Beeferman
发明人： William J. Byrne , Alexander H. Gruenstein , Douglas Beeferman
IPC分类号： G10L15/04
CPC分类号： G10L15/22 , G06F3/04842 , G06F3/167 , G06F17/2795 , G10L15/02 , G10L15/063 , G10L15/1822 , G10L15/26 , G10L2015/0631 , G10L2015/0635 , G10L2015/0638 , G10L2015/221
摘要： Predicting and learning users' intended actions on an electronic device based on free-form speech input. Users' actions can be monitored to develop of a list of carrier phrases having one or more actions that correspond to the carrier phrases. A user can speak a command into a device to initiate an action. The spoken command can be parsed and compared to a list of carrier phrases. If the spoken command matches one of the known carrier phrases, the corresponding action(s) can be presented to the user for selection. If the spoken command does not match one of the known carrier phrases, search results (e.g., Internet search results) corresponding to the spoken command can be presented to the user. The actions of the user in response to the presented action(s) and/or the search results can be monitored to update the list of carrier phrases.
摘要翻译：基于自由形式语音输入，预测和学习用户对电子设备的预期动作。可以监视用户的动作，以开发具有与运营商短语对应的一个或多个动作的运营商短语列表。用户可以向设备发出命令以启动动作。可以解析口头命令并将其与载体短语列表进行比较。如果口头命令与已知的运营商短语之一匹配，则可以将相应的动作呈现给用户进行选择。如果口头命令与已知的运营商短语之一不匹配，则可以向用户呈现与口语命令对应的搜索结果（例如，因特网搜索结果）。可以监视用户响应于所呈现的动作和/或搜索结果的动作以更新运营商短语列表。

6. 发明申请

US20130110492A1 Enhanced stability prediction for incrementally generated speech recognition hypotheses 有权
标题翻译：增强的语音识别假设的稳定性预测增强
公开(公告)号：US20130110492A1
公开(公告)日：2013-05-02
申请号：US13461033
申请日：2012-05-01
申请人： Ian C. McGraw , Alexander H. Gruenstein
发明人： Ian C. McGraw , Alexander H. Gruenstein
IPC分类号： G10L15/04 , G06F17/28
CPC分类号： G03F7/70708 , G03F7/707 , G03F7/70875 , G03F7/70908 , G10L15/08 , G10L2015/223 , H01L21/6831
摘要： Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for predicting the stability of speech recognition results. In one aspect, a method includes determining a length of time, or a number of occasions, in which a word has remained in an incremental speech recognizer's top hypothesis, and assigning a stability metric to the word based on the length of time or number of occasions.
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，用于预测语音识别结果的稳定性。在一个方面，一种方法包括确定一个单词在增量语音识别器的最高假设中保留的时间长度或多个场合，并且基于时间长度或时间长度来分配稳定度度量场合

7. 发明授权

US08489398B1 Disambiguation of spoken proper names 有权
标题翻译：消除口语专有名称
公开(公告)号：US08489398B1
公开(公告)日：2013-07-16
申请号：US13007528
申请日：2011-01-14
申请人： Alexander H. Gruenstein
发明人： Alexander H. Gruenstein
IPC分类号： G10L15/04 , G10L15/00
CPC分类号： G10L15/08 , G06F17/278 , G10L15/30
摘要： A method is performed by a communication device that is configured to communicate with a server over a network. The method includes outputting, to the server, speech data for spoken words; receiving, from the server, speech recognition candidates for a spoken word in the speech data; checking the speech recognition candidates against a database on the communication device; and selecting one or more of the speech recognition candidates for use by the communication device based on the checking.
摘要翻译：由通信设备执行方法，该通信设备被配置为通过网络与服务器进行通信。该方法包括向服务器输出用于说出的话的语音数据; 从所述服务器接收所述语音数据中的口语单词的语音识别候选; 根据通信设备上的数据库检查语音识别候选; 以及基于所述检查来选择所述通信设备使用的所述语音识别候选中的一个或多个。

8. 发明授权

US08909512B2 Enhanced stability prediction for incrementally generated speech recognition hypotheses based on an age of a hypothesis 有权
标题翻译：基于假设年龄的增量语音识别假设的增强的稳定性预测
公开(公告)号：US08909512B2
公开(公告)日：2014-12-09
申请号：US13461033
申请日：2012-05-01
申请人： Ian C. McGraw , Alexander H. Gruenstein
发明人： Ian C. McGraw , Alexander H. Gruenstein
IPC分类号： G06F17/28 , G06F17/27 , G10L15/08 , G10L15/22
CPC分类号： G03F7/70708 , G03F7/707 , G03F7/70875 , G03F7/70908 , G10L15/08 , G10L2015/223 , H01L21/6831
摘要： Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for predicting the stability of speech recognition results. In one aspect, a method includes determining a length of time, or a number of occasions, in which a word has remained in an incremental speech recognizer's top hypothesis, and assigning a stability metric to the word based on the length of time or number of occasions.
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，用于预测语音识别结果的稳定性。在一个方面，一种方法包括确定一个单词在增量语音识别器的最高假设中保留的时间长度或多个场合，并且基于时间长度或时间长度来分配稳定度度量场合

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