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

US11495208B2 Detecting potential significant errors in speech recognition results 有权
公开(公告)号：US11495208B2
公开(公告)日：2022-11-08
申请号：US15790117
申请日：2017-10-23
申请人： Nuance Communications, Inc.
发明人： William F. Ganong, III , Raghu Vemula , Robert Fleming
IPC分类号： G10L15/01 , G10L15/08 , G10L15/24
摘要： In some embodiments, recognition results produced by a speech processing system (which may include two or more recognition results, including a top recognition result and one or more alternative recognition results) based on an analysis of a speech input, are evaluated for indications of potential errors. In some embodiments, the indications of potential errors may include discrepancies between recognition results that are meaningful for a domain, such as medically-meaningful discrepancies. The evaluation of the recognition results may be carried out using any suitable criteria, including one or more criteria that differ from criteria used by an ASR system in determining the top recognition result and the alternative recognition results from the speech input. In some embodiments, a recognition result may additionally or alternatively be processed to determine whether the recognition result includes a word or phrase that is unlikely to appear in a domain to which speech input relates.

2. 发明申请

US20180158448A1 DETECTING POTENTIAL SIGNIFICANT ERRORS IN SPEECH RECOGNITION RESULTS 审中-公开
公开(公告)号：US20180158448A1
公开(公告)日：2018-06-07
申请号：US15790117
申请日：2017-10-23
申请人： Nuance Communications, Inc.
发明人： William F. Ganong, III , Raghu Vemula , Robert Fleming
IPC分类号： G10L15/01 , G10L15/08 , G10L15/24
CPC分类号： G10L15/01 , G10L15/08 , G10L15/24 , G10L2015/085
摘要： In some embodiments, recognition results produced by a speech processing system (which may include two or more recognition results, including a top recognition result and one or more alternative recognition results) based on an analysis of a speech input, are evaluated for indications of potential errors. In some embodiments, the indications of potential errors may include discrepancies between recognition results that are meaningful for a domain, such as medically-meaningful discrepancies. The evaluation of the recognition results may be carried out using any suitable criteria, including one or more criteria that differ from criteria used by an ASR system in determining the top recognition result and the alternative recognition results from the speech input. In some embodiments, a recognition result may additionally or alternatively be processed to determine whether the recognition result includes a word or phrase that is unlikely to appear in a domain to which speech input relates.

3. 发明申请

US20150248882A1 DETECTING POTENTIAL SIGNIFICANT ERRORS IN SPEECH RECOGNITION RESULTS 有权
标题翻译：检测语音识别结果中的潜在重要错误
公开(公告)号：US20150248882A1
公开(公告)日：2015-09-03
申请号：US14713372
申请日：2015-05-15
申请人： Nuance Communications, Inc.
发明人： William F. Ganong, III , Raghu Vemula , Robert Fleming
IPC分类号： G10L15/01
CPC分类号： G10L15/01 , G10L15/08 , G10L15/24 , G10L2015/085
摘要： In some embodiments, recognition results produced by a speech processing system (which may include two or more recognition results, including a top recognition result and one or more alternative recognition results) based on an analysis of a speech input, are evaluated for indications of potential errors. In some embodiments, the indications of potential errors may include discrepancies between recognition results that are meaningful for a domain, such as medically-meaningful discrepancies. The evaluation of the recognition results may be carried out using any suitable criteria, including one or more criteria that differ from criteria used by an ASR system in determining the top recognition result and the alternative recognition results from the speech input. In some embodiments, a recognition result may additionally or alternatively be processed to determine whether the recognition result includes a word or phrase that is unlikely to appear in a domain to which speech input relates.
摘要翻译：在一些实施例中，基于语音输入的分析，由语音处理系统（其可以包括两个或多个识别结果，包括顶部识别结果和一个或多个替代识别结果）产生的识别结果被评估用于潜在的指示错误。在一些实施例中，潜在错误的迹象可能包括对域有意义的识别结果之间的差异，例如医学上有意义的差异。识别结果的评估可以使用任何合适的标准进行，包括与ASR系统在确定最高识别结果和来自语音输入的替代识别结果时使用的标准不同的一个或多个标准。在一些实施例中，识别结果可以附加地或替代地被处理以确定识别结果是否包括不太可能出现在与语音输入相关的域中的单词或短语。

4. 发明授权

US09564126B2 Using models to detect potential significant errors in speech recognition results 有权
标题翻译：使用模型来检测语音识别结果中的潜在重大错误
公开(公告)号：US09564126B2
公开(公告)日：2017-02-07
申请号：US14557321
申请日：2014-12-01
申请人： Nuance Communications, Inc.
发明人： William F. Ganong, III , Raghu Vemula , Robert Fleming
IPC分类号： G10L15/18 , G10L15/01 , G10L15/26 , G10L15/183
CPC分类号： G10L15/18 , G10L15/01 , G10L15/183 , G10L15/26
摘要： In some embodiments, a recognition result produced by a speech processing system based on an analysis of a speech input is evaluated for indications of potential errors. In some embodiments, sets of words/phrases that may be acoustically similar or otherwise confusable, the misrecognition of which can be significant in the domain, may be used together with a language model to evaluate a recognition result to determine whether the recognition result includes such an indication. In some embodiments, a word/phrase of a set that appears in the result is iteratively replaced with each of the other words/phrases of the set. The result of the replacement may be evaluated using a language model to determine a likelihood of the newly-created string of words appearing in a language and/or domain. The likelihood may then be evaluated to determine whether the result of the replacement is sufficiently likely for an alert to be triggered.
摘要翻译：在一些实施例中，评估由基于语音输入的分析的语音处理系统产生的识别结果，用于潜在错误的指示。在一些实施例中，可以声学上相似或以其他方式混淆的词/短语集合，其识别在域中可能是重要的，可以与语言模型一起使用以评估识别结果，以确定识别结果是否包括这样的指示。在一些实施例中，出现在结果中的集合的单词/短语被迭代地替换为该集合中的每个其他单词/短语。可以使用语言模型来评估替换的结果，以确定在语言和/或域中出现的新创建的字符串的可能性。然后可以评估可能性以确定替换的结果是否足以触发警报。

5. 发明授权

US09343062B2 Detecting potential medically-significant errors in speech recognition results 有权
公开(公告)号：US09343062B2
公开(公告)日：2016-05-17
申请号：US14557289
申请日：2014-12-01
申请人： Nuance Communications, Inc.
发明人： William F. Ganong, III , Raghu Vemula , Robert Fleming
IPC分类号： G10L15/22 , G10L15/08 , G10L15/18
CPC分类号： G10L15/08 , G10L15/1815 , G10L15/1822 , G10L15/22 , G10L2015/088
摘要： In some embodiments, the recognition results produced by a speech processing system (which may include two or more recognition results, including a top recognition result and one or more alternative recognition results) based on an analysis of a speech input, are evaluated for indications of potential significant errors. In some embodiments, the recognition results may be evaluated to determine whether a meaning of any of the alternative recognition results differs from a meaning of the top recognition result in a manner that is significant for a domain, such as the medical domain. In some embodiments, words and/or phrases that may be confused by an ASR system may be determined and associated in sets of words and/or phrases. Words and/or phrases that may be determined include those that change a meaning of a phrase or sentence when included in the phrase/sentence.

6. 发明申请

US20150088517A1 DETECTING POTENTIAL SIGNIFICANT ERRORS IN SPEECH RECOGNITION RESULTS 有权
公开(公告)号：US20150088517A1
公开(公告)日：2015-03-26
申请号：US14557313
申请日：2014-12-01
申请人： Nuance Communications, Inc.
发明人： William F. Ganong, III , Raghu Vemula , Robert Fleming
IPC分类号： G10L15/18
CPC分类号： G10L15/08 , G10L15/1815 , G10L15/1822 , G10L15/22 , G10L2015/088
摘要： In some embodiments, the recognition results produced by a speech processing system (which may include two or more recognition results, including a top recognition result and one or more alternative recognition results) based on an analysis of a speech input, are evaluated for indications of potential significant errors. In some embodiments, the recognition results may be evaluated to determine whether a meaning of any of the alternative recognition results differs from a meaning of the top recognition result in a manner that is significant for a domain, such as the medical domain. In some embodiments, words and/or phrases that may be confused by an ASR system may be determined and associated in sets of words and/or phrases. Words and/or phrases that may be determined include those that change a meaning of a phrase or sentence when included in the phrase/sentence.

7. 发明申请

US20150088516A1 DETECTING POTENTIAL SIGNIFICANT ERRORS IN SPEECH RECOGNITION RESULTS 有权
公开(公告)号：US20150088516A1
公开(公告)日：2015-03-26
申请号：US14557304
申请日：2014-12-01
申请人： Nuance Communications, Inc.
发明人： William F. Ganong, III , Raghu Vemula , Robert Fleming
IPC分类号： G10L15/18
CPC分类号： G10L15/08 , G10L15/1815 , G10L15/1822 , G10L15/22 , G10L2015/088
摘要： In some embodiments, the recognition results produced by a speech processing system (which may include two or more recognition results, including a top recognition result and one or more alternative recognition results) based on an analysis of a speech input, are evaluated for indications of potential significant errors. In some embodiments, the recognition results may be evaluated to determine whether a meaning of any of the alternative recognition results differs from a meaning of the top recognition result in a manner that is significant for a domain, such as the medical domain. In some embodiments, words and/or phrases that may be confused by an ASR system may be determined and associated in sets of words and/or phrases. Words and/or phrases that may be determined include those that change a meaning of a phrase or sentence when included in the phrase/sentence.

8. 发明授权

US09818398B2 Detecting potential significant errors in speech recognition results 有权
公开(公告)号：US09818398B2
公开(公告)日：2017-11-14
申请号：US14713372
申请日：2015-05-15
申请人： Nuance Communications, Inc.
发明人： William F. Ganong, III , Raghu Vemula , Robert Fleming
IPC分类号： G10L15/22 , G10L15/01 , G10L15/08 , G10L15/24
CPC分类号： G10L15/01 , G10L15/08 , G10L15/24 , G10L2015/085
摘要： In some embodiments, recognition results produced by a speech processing system (which may include two or more recognition results, including a top recognition result and one or more alternative recognition results) based on an analysis of a speech input, are evaluated for indications of potential errors. In some embodiments, the indications of potential errors may include discrepancies between recognition results that are meaningful for a domain, such as medically-meaningful discrepancies. The evaluation of the recognition results may be carried out using any suitable criteria, including one or more criteria that differ from criteria used by an ASR system in determining the top recognition result and the alternative recognition results from the speech input. In some embodiments, a recognition result may additionally or alternatively be processed to determine whether the recognition result includes a word or phrase that is unlikely to appear in a domain to which speech input relates.

9. 发明授权

US09443509B2 Detecting potential medically-significant errors in speech recognition results 有权
公开(公告)号：US09443509B2
公开(公告)日：2016-09-13
申请号：US14557304
申请日：2014-12-01
申请人： Nuance Communications, Inc.
发明人： William F. Ganong, III , Raghu Vemula , Robert Fleming
IPC分类号： G10L15/22 , G10L15/08 , G10L15/18
CPC分类号： G10L15/08 , G10L15/1815 , G10L15/1822 , G10L15/22 , G10L2015/088
摘要： In some embodiments, the recognition results produced by a speech processing system (which may include two or more recognition results, including a top recognition result and one or more alternative recognition results) based on an analysis of a speech input, are evaluated for indications of potential significant errors. In some embodiments, the recognition results may be evaluated to determine whether a meaning of any of the alternative recognition results differs from a meaning of the top recognition result in a manner that is significant for a domain, such as the medical domain. In some embodiments, words and/or phrases that may be confused by an ASR system may be determined and associated in sets of words and/or phrases. Words and/or phrases that may be determined include those that change a meaning of a phrase or sentence when included in the phrase/sentence.

10. 发明申请

US20150248883A1 DETECTING POTENTIAL SIGNIFICANT ERRORS IN SPEECH RECOGNITION RESULTS 有权
标题翻译：检测语音识别结果中的潜在重要错误
公开(公告)号：US20150248883A1
公开(公告)日：2015-09-03
申请号：US14713433
申请日：2015-05-15
申请人： Nuance Communications, Inc.
发明人： William F. Ganong, III , Raghu Vemula , Robert Fleming
IPC分类号： G10L15/01 , G10L15/08
CPC分类号： G10L15/01 , G10L15/08 , G10L15/1815 , G10L2015/085
摘要： In some embodiments, the recognition results produced by a speech processing system (which may include a top recognition result and one or more alternative recognition results) based on an analysis of a speech input, are evaluated for indications of potential significant errors. In some embodiments, the recognition results may be evaluated to determine whether a meaning of any of the alternative recognition results differs from a meaning of the top recognition result in a manner that is significant for the domain. In some embodiments, one or more of the recognition results may be evaluated to determine whether the result(s) include one or more words or phrases that, when included in a result, would change a meaning of the result in a manner that would be significant for the domain.
摘要翻译：在一些实施例中，基于语音输入的分析，由语音处理系统（其可以包括顶部识别结果和一个或多个替代识别结果）产生的识别结果被评估用于潜在重大错误的指示。在一些实施例中，可以评估识别结果以确定任何替代识别结果的含义以对于域有意义的方式与顶部识别结果的含义不同。在一些实施例中，可以评估一个或多个识别结果以确定结果是否包括一个或多个单词或短语，当被包括在结果中时，将以以下方式改变结果的含义：对领域有重要意义

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