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

CA2683292C USING WORD CONFIDENCE SCORE, INSERTION AND SUBSTITUTION THRESHOLDS FOR SELECTED WORDS IN SPEECH RECOGNITION 未知
公开(公告)号：CA2683292C
公开(公告)日：2018-02-27
申请号：CA2683292
申请日：2009-10-22
申请人： ADACEL INC
发明人： SHU CHANG-QING
IPC分类号： G10L15/02
摘要： A method and system for improving the accuracy of a speech recognition system using word confidence score (WCS) processing is introduced. Parameters in a decoder are selected to minimize a weighted total error rate, such that deletion errors are weighted more heavily than substitution and insertion errors. The occurrence distribution in WCS is different depending on whether the word was correctly identified and based on the type of error. This is used to determine thresholds in WCS for insertion and substitution errors. By processing the hypothetical word (HYP) (output of the decoder), a mHYP (modified HYP) is determined. In some circumstances, depending on the WCS's value in relation to insertion and substitution threshold values, mHYP is set equal to: null, a substituted HYP, or HYP.

2. 发明专利

CA2683292A1 USING WORD CONFIDENCE SCORE, INSERTION AND SUBSTITUTION THRESHOLDS FOR SELECTED WORDS IN SPEECH RECOGNITION 未知
公开(公告)号：CA2683292A1
公开(公告)日：2010-04-24
申请号：CA2683292
申请日：2009-10-22
申请人： ADACEL INC
发明人： SHU CHANG-QING
IPC分类号： G10L15/02
摘要： A method and system for improving the accuracy of a speech recognition system using word confidence score (WCS) processing is introduced. Parameters in a decoder are selected to minimize a weighted total error rate, such that deletion errors are weighted more heavily than substitution and insertion errors. The occurrence distribution in WCS is different depending on whether the word was correctly identified and based on the type of error. This is used to determine thresholds in WCS for insertion and substitution errors. By processing the hypothetical word (HYP) (output of the decoder), a mHYP (modified HYP) is determined. In some circumstances, depending on the WCS's value in relation to insertion and substitution threshold values, mHYP is set equal to: null, a substituted HYP, or HYP.

3. 发明专利

CA2682643A1 CONFIRMATION SYSTEM FOR COMMAND OR SPEECH RECOGNITION USING ACTIVATION MEANS 未知
公开(公告)号：CA2682643A1
公开(公告)日：2008-09-12
申请号：CA2682643
申请日：2007-11-14
申请人： ADACEL INC
发明人： DESROCHERS DANIEL
IPC分类号： G10L15/22
摘要： A system and method for confirming command or speech recognition results returned by an automatic speech recognition (ASR) engine from a command issu ed by an operator of a vehicle or platform, such as an aircraft or unmanned air-vehicle (UAV). The operator transmits a command signal to the ASR engine , initiated by an activation means, such as a push-button (formally known as push-to-talk or push-to-recognize). A recognition result is communicated to the user and the system awaits the confirmation for a limited period of tim e. During this period, in one embodiment, a low tone with high prosody is pl ayed to notify the user that the system is ready to receive the confirmation . If the user quickly presses and releases the push-button a predetermined n umber of times (for instance, twice to make a double-click), the result is c onfirmed and the ASR forwards a command signal to a system controlled thereb y. Otherwise, the ASR waits for another speech command.

4. 发明申请

WO2008099260A2 SYSTEM AND METHOD FOR GENERATING AND USING AN ARRAY OF DYNAMIC GRAMMARS 审中-公开
标题翻译：用于生成和使用动态粒子阵列的系统和方法
公开(公告)号：WO2008099260A2
公开(公告)日：2008-08-21
申请号：PCT/IB2008/000312
申请日：2008-02-13
申请人： ADACEL, INC. , DESROCHERS, Daniel
发明人： DESROCHERS, Daniel
IPC分类号： G10L15/00 , B60W50/08 , B64D47/00 , G10L15/06 , G10L15/08
CPC分类号： G10L2015/228
摘要： A system and method for generating dynamic grammars for use by a speech recognition system in response to signals from sensors indicative of the position and/or movement of a vehicle or platform, such as an aircraft or helicopter.
摘要翻译：一种用于响应于来自传感器的信号产生语音识别系统使用的动态语法的系统和方法，其指示诸如飞机或直升机的车辆或平台的位置和/或移动。

5. 发明申请

WO2008107735A3 CONFIRMATION SYSTEM FOR COMMAND OR SPEECH RECOGNITION USING ACTIVATION MEANS 审中-公开
公开(公告)号：WO2008107735A3
公开(公告)日：2008-09-12
申请号：PCT/IB2007/004573
申请日：2007-11-14
申请人： ADACEL, INC. , DESROCHERS, DANIEL
发明人： DESROCHERS, DANIEL
IPC分类号： G10L15/22 , G10L15/00 , G10L13/00
摘要： A system and method for confirming command or speech recognition results returned by an automatic speech recognition (ASR) engine from a command issued by an operator of a vehicle or platform, such as an aircraft or unmanned air-vehicle (UAV). The operator transmits a command signal to the ASR engine, initiated by an activation means, such as a push-button (formally known as push-to-talk or push-to-recognize). A recognition result is communicated to the user and the system awaits the confirmation for a limited period of time. During this period, in one embodiment, a low tone with high prosody is played to notify the user that the system is ready to receive the confirmation. If the user quickly presses and releases the push-button a predetermined number of times (for instance, twice to make a double-click), the result is confirmed and the ASR forwards a command signal to a system controlled thereby. Otherwise, the ASR waits for another speech command.

6. 发明专利

CA2696514A1 SPEECH RECOGNITION LEARNING SYSTEM AND METHOD 未知
公开(公告)号：CA2696514A1
公开(公告)日：2010-09-13
申请号：CA2696514
申请日：2010-03-11
申请人： ADACEL INC
发明人： BOURDON FRANCOIS
IPC分类号： G10L15/06 , G10L15/18
摘要： One or more embodiments include a speech recognition learning system for improved speech recognition. The learning system may include a speech optimizing system. The optimizing system may receive a first stimulus data package including spoken utterances having at least one phoneme, and contextual information. A number of result data packages may be retrieved which include stored spoken utterances and contextual information. A determination may be made as to whether the first stimulus data package requires improvement. A second stimulus data package may be generated based on the determination. A number of speech recognition implementation rules for implementing the second stimulus data package may be received. The rules may be associated with the contextual information. A determination may be made as to whether the second stimulus data package requires further improvement. Based on the determination, one or more additional speech recognition implementation rules for improved speech recognition may be generated.

7. 发明专利

CA2676339A1 SYSTEM AND METHOD FOR GENERATING AND USING AN ARRAY OF DYNAMIC GRAMMARS 未知
公开(公告)号：CA2676339A1
公开(公告)日：2008-08-21
申请号：CA2676339
申请日：2008-02-13
申请人： ADACEL INC
发明人： DESROCHERS DANIEL
IPC分类号： G10L15/00 , B60W50/08 , B64D47/00 , G10L15/06 , G10L15/08
摘要： A system and method for generating dynamic grammars for use by a speech r ecognition system in response to signals from sensors indicative of the posi tion and/or movement of a vehicle or platform, such as an aircraft or helico pter.

8. 发明专利

CA2696514C SPEECH RECOGNITION LEARNING SYSTEM AND METHOD 未知
公开(公告)号：CA2696514C
公开(公告)日：2016-06-07
申请号：CA2696514
申请日：2010-03-11
申请人： ADACEL INC
发明人： BOURDON FRANCOIS
IPC分类号： G10L15/06
摘要： One or more embodiments include a speech recognition learning system for improved speech recognition. The learning system may include a speech optimizing system. The optimizing system may receive a first stimulus data package including spoken utterances having at least one phoneme, and contextual information. A number of result data packages may be retrieved which include stored spoken utterances and contextual information. A determination may be made as to whether the first stimulus data package requires improvement. A second stimulus data package may be generated based on the determination. A number of speech recognition implementation rules for implementing the second stimulus data package may be received. The rules may be associated with the contextual information. A determination may be made as to whether the second stimulus data package requires further improvement. Based on the determination, one or more additional speech recognition implementation rules for improved speech recognition may be generated.

9. 发明申请

WO2008099260A3 SYSTEM AND METHOD FOR GENERATING AND USING AN ARRAY OF DYNAMIC GRAMMARS 审中-公开
标题翻译：用于生成和使用动态语法阵列的系统和方法
公开(公告)号：WO2008099260A3
公开(公告)日：2008-10-16
申请号：PCT/IB2008000312
申请日：2008-02-13
申请人： ADACEL INC , DESROCHERS DANIEL
发明人： DESROCHERS DANIEL
IPC分类号： G10L15/00 , B60W50/08 , B64D47/00 , G10L15/06 , G10L15/08
CPC分类号： G10L2015/228
摘要： A system and method for generating dynamic grammars for use by a speech recognition system in response to signals from sensors indicative of the position and/or movement of a vehicle or platform, such as an aircraft or helicopter.
摘要翻译：一种用于响应于来自指示诸如飞机或直升机之类的交通工具或平台的位置和/或运动的传感器的信号而生成供语音识别系统使用的动态语法的系统和方法。

10. 发明申请

WO2008107735A2 CONFIRMATION SYSTEM FOR COMMAND OR SPEECH RECOGNITION USING ACTIVATION MEANS 审中-公开
标题翻译：使用激活手段的命令或语音识别的确认系统
公开(公告)号：WO2008107735A2
公开(公告)日：2008-09-12
申请号：PCT/IB2007004573
申请日：2007-11-14
申请人： ADACEL INC , DESROCHERS DANIEL
发明人： DESROCHERS DANIEL
CPC分类号： G10L15/22
摘要： A system and method for confirming command or speech recognition results returned by an automatic speech recognition (ASR) engine from a command issued by an operator of a vehicle or platform, such as an aircraft or unmanned air-vehicle (UAV). The operator transmits a command signal to the ASR engine, initiated by an activation means, such as a push-button (formally known as push-to-talk or push-to-recognize). A recognition result is communicated to the user and the system awaits the confirmation for a limited period of time. During this period, in one embodiment, a low tone with high prosody is played to notify the user that the system is ready to receive the confirmation. If the user quickly presses and releases the push-button a predetermined number of times (for instance, twice to make a double-click), the result is confirmed and the ASR forwards a command signal to a system controlled thereby. Otherwise, the ASR waits for another speech command.
摘要翻译：一种用于根据由诸如飞行器或无人驾驶飞行器（UAV）的车辆或平台的操作者发出的命令来确认由自动语音识别（ASR）引擎返回的命令或语音识别结果的系统和方法。操作者向ASR引擎发送命令信号，该激活装置由诸如按钮（正式称为即按即说或者即插即用）的激活装置发起。将识别结果传达给用户，系统等待有限的确认时间。在此期间，在一个实施例中，播放具有高韵律的低音，以通知用户系统准备好接收确认。如果用户快速按下并释放按钮预定次数（例如，两次进行双击），则确认结果，并且ASR将命令信号转发到由其控制的系统。否则，ASR等待另一个语音命令。

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