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

EP2721604B1 HEADSET SIGNAL MULTIPLEXING SYSTEM AND METHOD 有权
标题翻译：头戴式信号复用系统和方法
公开(公告)号：EP2721604B1
公开(公告)日：2017-08-16
申请号：EP12801061.8
申请日：2012-06-14
申请人： Vocollect, Inc.
发明人： BRAHO, Keith
IPC分类号： G10K11/16
CPC分类号： H04R3/12 , H04R1/10 , H04R2201/107 , H04R2420/07

2. 发明公开

EP2005417A2 METHODS AND SYSTEMS FOR OPTIMIZING MODEL ADAPTATION FOR A SPEECH RECOGNITION SYSTEM 审中-公开
标题翻译：方法和系统优化模型调整了语音识别系统
公开(公告)号：EP2005417A2
公开(公告)日：2008-12-24
申请号：EP07759818.3
申请日：2007-03-30
申请人： Vocollect, Inc.
发明人： BRAHO, Keith , PIKE, Jeffrey
IPC分类号： G10L15/06
CPC分类号： G10L15/01 , G10L15/07
摘要： Methods are disclosed for identifying possible errors made by a speech recognition system without using a transcript of words input to the system. A method for model adaptation for a speech recognition system includes determining an error rate (315), corresponding to either recognition of instances of a word or recognition of instances of various words, without using a transcript of words input to the system. The method may further include adjusting an adaptation 320, of the model for the word or various models for the various words, based on the error rate. Apparatus are disclosed for identifying possible errors made by a speech recognition system without using a transcript of words input to the system. An apparatus for model adaptation for a speech recognition system includes a processor 210 adapted to estimate an error rate, corresponding to either recognition of instances of a word or recognition of instances of various words, without using a transcript of words input to the system. The apparatus may further include a controller 225 adapted to adjust an adaptation of the model 235 for the word or various models for the various words, based on the error rate.

3. 发明公开

EP2005416A2 METHODS AND SYSTEMS FOR ASSESSING AND IMPROVING THE PERFORMANCE OF A SPEECH RECOGNITION SYSTEM 无效
标题翻译：方法和系统评估和提高语音识别系统的性能
公开(公告)号：EP2005416A2
公开(公告)日：2008-12-24
申请号：EP07759805.0
申请日：2007-03-30
申请人： Vocollect, Inc.
发明人： BRAHO, Keith , PIKE, Jeffrey , EL-JAROUDI, Amro , PIKE, Lori , LAUGHERY, Michael
IPC分类号： G10L15/00 , G10L15/06
CPC分类号： G10L15/01 , G10L15/07
摘要： Methods are disclosed for identifying possible errors made by a speech recognition system without using a transcript of words input to the system. A method for model adaptation for a speech recognition system includes determining an error rate (315), corresponding to either recognition of instances of a word or recognition of instances of various words, without using a transcript of words input to the system. The method may further include adjusting an adaptation 320, of the model for the word or various models for the various words, based on the error rate. Apparatus are disclosed for identifying possible errors made by a speech recognition system without using a transcript of words input to the system. An apparatus for model adaptation for a speech recognition system includes a processor 210 adapted to estimate an error rate, corresponding to either recognition of instances of a word or recognition of instances of various words, without using a transcript of words input to the system. The apparatus may further include a controller 225 adapted to adjust an adaptation of the model 235 for the word or various models for the various words, based on the error rate.

4. 发明公开

EP2721604A1 HEADSET SIGNAL MULTIPLEXING SYSTEM AND METHOD 有权
标题翻译：系统和方法复用耳机SIGNALS
公开(公告)号：EP2721604A1
公开(公告)日：2014-04-23
申请号：EP12801061.8
申请日：2012-06-14
申请人： Vocollect, Inc.
发明人： BRAHO, Keith
IPC分类号： G10K11/16
CPC分类号： H04R3/12 , H04R1/10 , H04R2201/107 , H04R2420/07
摘要： A system and method for supplying power to a headset, and for transmitting multiple signals generated in the headset to a terminal using frequency division multiplexing. An audio signal (66) and a carrier signal (68) are generated in the terminal and summed together to form a composite uplink signal (70). The composite uplink signal (70) is provided to a headset (14) over a first physical channel (28). At the headset (14), the audio and carrier signals are separated, and the carrier signal (68) is used to generate power in the headset. Signals generated by a plurality of acoustic sensors (60, 62) in the headset are combined using frequency division multiplexing to generate a composite downlink signal (76), which is transmitted to the terminal over a second physical channel.

5. 发明授权

EP2005418B1 METHODS AND SYSTEMS FOR ADAPTING A MODEL FOR A SPEECH RECOGNITION SYSTEM 有权
标题翻译：方法和系统模式过程语音识别系统适应
公开(公告)号：EP2005418B1
公开(公告)日：2012-06-27
申请号：EP07759840.7
申请日：2007-03-30
申请人： Vocollect, Inc.
发明人： BRAHO, Keith , PIKE, Jeffrey , PIKE, Lori, A.
IPC分类号： G10L15/06 , G10L15/22 , G10L15/28
CPC分类号： G10L15/01 , G10L15/07
摘要： Methods are disclosed for identifying possible errors made by a speech recognition system without using a transcript of words input to the system. A method for model adaptation for a speech recognition system includes determining an error rate (315), corresponding to either recognition of instances of a word or recognition of instances of various words, without using a transcript of words input to the system. The method may further include adjusting an adaptation 320, of the model for the word or various models for the various words, based on the error rate. Apparatus are disclosed for identifying possible errors made by a speech recognition system without using a transcript of words input to the system. An apparatus for model adaptation for a speech recognition system includes a processor 210 adapted to estimate an error rate, corresponding to either recognition of instances of a word or recognition of instances of various words, without using a transcript of words input to the system. The apparatus may further include a controller 225 adapted to adjust an adaptation of the model 235 for the word or various models for the various words, based on the error rate.

6. 发明公开

EP2005418A2 METHODS AND SYSTEMS FOR ADAPTING A MODEL FOR A SPEECH RECOGNITION SYSTEM 有权
标题翻译：方法和系统模式过程语音识别系统适应
公开(公告)号：EP2005418A2
公开(公告)日：2008-12-24
申请号：EP07759840.7
申请日：2007-03-30
申请人： Vocollect, Inc.
发明人： BRAHO, Keith , PIKE, Jeffrey , PIKE, Lori, A.
IPC分类号： G10L15/06 , G10L15/22 , G10L15/28
CPC分类号： G10L15/01 , G10L15/07
摘要： Methods are disclosed for identifying possible errors made by a speech recognition system without using a transcript of words input to the system. A method for model adaptation for a speech recognition system includes determining an error rate (315), corresponding to either recognition of instances of a word or recognition of instances of various words, without using a transcript of words input to the system. The method may further include adjusting an adaptation 320, of the model for the word or various models for the various words, based on the error rate. Apparatus are disclosed for identifying possible errors made by a speech recognition system without using a transcript of words input to the system. An apparatus for model adaptation for a speech recognition system includes a processor 210 adapted to estimate an error rate, corresponding to either recognition of instances of a word or recognition of instances of various words, without using a transcript of words input to the system. The apparatus may further include a controller 225 adapted to adjust an adaptation of the model 235 for the word or various models for the various words, based on the error rate.

7. 发明公开

EP3627497A1 METHODS AND SYSTEMS FOR ASSESSING AND IMPROVING THE PERFORMANCE OF A SPEECH RECOGNITION SYSTEM 有权
公开(公告)号：EP3627497A1
公开(公告)日：2020-03-25
申请号：EP19203259.7
申请日：2007-03-30
申请人： Vocollect, Inc.
发明人： BRAHO, Keith , PIKE, Lori , PIKE, Jeffrey , LAUGHERY, Michael , EL-JAROUDI, Amro
IPC分类号： G10L15/01 , G10L15/07 , G10L15/06 , G10L15/22 , G10L15/28
摘要： A method for assessing a performance of a speech recognition system may include determining a grade 315, 320, corresponding to either recognition of instances of a word or recognition of instances of various words among a set of words, wherein the grade indicates a level of the performance of the system and the grade is based on a recognition rate and at least one recognition factor. An apparatus for assessing a performance of a speech recognition system may include a processor 224 that determines a grade, corresponding to either recognition of instances of a word or recognition of instances of various words among a set of words, wherein the grade indicates a level of the performance of the system and wherein the grade is based on a recognition rate and at least one recognition factor.

8. 发明公开

EP1851758A1 METHODS AND SYSTEMS FOR CONSIDERING INFORMATION ABOUT AN EXPECTED RESPONSE WHEN PEREORMING SPEECH RECOGNITION 审中-公开
标题翻译：方法和系统审议信息对预期的回答语音识别的实现
公开(公告)号：EP1851758A1
公开(公告)日：2007-11-07
申请号：EP06734403.6
申请日：2006-02-02
申请人： Vocollect, Inc.
发明人： PIKE, Jeffrey , EL-JAROUDI, Amro , BRAHO, Keith
IPC分类号： G10L15/22 , G10L15/06
CPC分类号： G10L15/22 , G10L15/065 , G10L2015/228
摘要： A speech recognition system receives and analyzes speech input from a user in order to recognize and accept a response from the user. Under certain conditions, information about the response expected from the user may be available, In these situations, the available information about the expected response is used to modify the behavior of the speech recognition system by taking this information into account. In one embodiment, the modified behavior of the speech recognition system comprises adjusting the rejection threshold when speech input matches the predetermined expected response. The modified behavior of the speech recognition system according to other embodiments of the invention include comparing the observed speech features to the models of the expected response separately from the usual hypothesis search in order to speed up the recognition system; modifying the usual hypothesis search to emphasize the expected response; updating and adapting the models when the recognized speech matches the expected response to improve the accuracy of the recognition system
摘要翻译：一种语音识别系统接收并以识别和接受来自用户的响应来自用户的分析性的语音。在某些条件下，关于从用户预期是可用的，在合成的情况下的响应的信息，关于所述预期响应的可用信息被用于通过取该信息考虑在内来修改所述语音识别系统的行为。在一个，语音识别系统的实施例修改的行为包括：调整所述拒绝阈值。当版speechInput预定期望响应相匹配。语音识别系统gemäß到本发明的其它实施例的修改的行为包括比较所观察到的语音特征来从以加快识别系统通常假设搜索分别预期响应的模型; 修改通常假设搜索以强调预期响应; 更新和适应的机型当识别的语音预期的响应相匹配，以提高识别系统的准确度

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