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

US11348574B2 Meeting-adapted language model for speech recognition 有权
公开(公告)号：US11348574B2
公开(公告)日：2022-05-31
申请号：US16531435
申请日：2019-08-05
申请人： Microsoft Technology Licensing, LLC
发明人： Ziad Al Bawab , Anand U Desai , Shuangyu Chang , Amit K Agarwal , Zoltan Romocsa , Christopher H Basoglu , Nathan E Wohlgemuth
IPC分类号： G10L15/193 , G06Q10/10 , G10L15/197 , G10L15/22 , G10L15/30
摘要： A system includes acquisition of meeting data associated with a meeting, determination of a plurality of meeting participants based on the acquired meeting data, acquisition of e-mail data associated with each of the plurality of meeting participants, generation of a meeting language model based on the acquired e-mail data and the meeting data, and transcription of audio associated with the meeting based on the meeting language model.

2. 发明授权

US10679610B2 Eyes-off training for automatic speech recognition 有权
公开(公告)号：US10679610B2
公开(公告)日：2020-06-09
申请号：US16036721
申请日：2018-07-16
申请人： Microsoft Technology Licensing, LLC
发明人： Hemant Malhotra , Shuangyu Chang , Pradip Kumar Fatehpuria
IPC分类号： G10L15/06 , G06F40/279 , G06F40/166 , G10L15/02 , G10L15/26
摘要： A method for eyes-off training of a dictation system includes translating an audio signal featuring speech audio of a speaker into an initial recognized text using a previously-trained general language model. The initial recognized text is provided to the speaker for error correction. The audio signal is re-translated into an updated recognized text using a specialized language model biased to recognize words included in the corrected text. The general language model is retrained in an “eyes-off” manner, based on the audio signal and the updated recognized text.

3. 发明申请

US20190287519A1 CORRECTION OF SPEECH RECOGNITION ON REPETITIVE QUERIES 审中-公开
公开(公告)号：US20190287519A1
公开(公告)日：2019-09-19
申请号：US15920231
申请日：2018-03-13
申请人： Microsoft Technology Licensing, LLC
发明人： Meryem Pinar Donmez Ediz , Ranjitha Gurunath Kulkarni , Shuangyu Chang , Nitin Kamra
IPC分类号： G10L15/197 , G10L15/22 , G10L15/18 , G10L15/01 , G10L15/07
摘要： Disclosed in various examples are methods, systems, and machine-readable mediums for providing improved computer implemented speech recognition by detecting and correcting speech recognition errors during a speech session. The system recognizes repeated speech commands from a user in a speech session that are similar or identical to each other. To correct these repeated errors, the system creates a customized language model that is then utilized by the language modeler to produce a refined prediction of the meaning of the repeated speech commands. The custom language model may comprise clusters of similar past predictions of speech commands from the speech session of the user.

4. 发明授权

US09761220B2 Language modeling based on spoken and unspeakable corpuses 有权
公开(公告)号：US09761220B2
公开(公告)日：2017-09-12
申请号：US14711447
申请日：2015-05-13
申请人： Microsoft Technology Licensing, LLC
发明人： Michael Levit , Shuangyu Chang , Benoit Dumoulin
IPC分类号： G10L15/06 , G10L15/10 , G10L15/14 , G10L15/18 , G10L15/19
CPC分类号： G10L15/063 , G10L15/10 , G10L15/14 , G10L15/18 , G10L15/19 , G10L2015/0633 , G10L2015/0635
摘要： A computer system for language modeling may collect training data from one or more information sources, generate a spoken corpus containing text of transcribed speech, and generate a typed corpus containing typed text. The computer system may derive feature vectors from the spoken corpus, analyze the typed corpus to determine feature vectors representing items of typed text, and generate an unspeakable corpus by filtering the typed corpus to remove each item of typed text represented by a feature vector that is within a similarity threshold of a feature vector derived from the spoken corpus. The computer system may derive feature vectors from the unspeakable corpus and train a classifier to perform discriminative data selection for language modeling based on the feature vectors derived from the spoken corpus and the feature vectors derived from the unspeakable corpus.

5. 发明授权

US11562738B2 Online language model interpolation for automatic speech recognition 有权
公开(公告)号：US11562738B2
公开(公告)日：2023-01-24
申请号：US16665574
申请日：2019-10-28
申请人： Microsoft Technology Licensing, LLC
发明人： Ziad Al Bawab , Anand U Desai , Shuangyu Chang , Amit K Agarwal , Zoltan Romocsa , Veljko Miljanic , Aadyot Bhatnagar , Hosam Khalil , Christopher Basoglu
IPC分类号： G10L15/00 , G10L15/18 , G10L15/193 , G06Q10/10 , G10L15/197 , G10L15/22 , G10L15/30
摘要： A system includes acquisition of a domain grammar, determination of an interpolated grammar based on the domain grammar and a base grammar, determination of a delta domain grammar based on an augmented first grammar and the interpolated grammar, determination of an out-of-vocabulary class based on the domain grammar and the base grammar, insertion of the out-of-vocabulary class into a composed transducer composed of the augmented first grammar and one or more other transducers to generate an updated composed transducer, composition of the delta domain grammar and the updated composed transducer, and application of the composition of the delta domain grammar and the updated composed transducer to an output of an acoustic model.

6. 发明授权

US09552817B2 Incremental utterance decoder combination for efficient and accurate decoding 有权
标题翻译：增量语音解码器组合，用于高效准确的解码
公开(公告)号：US09552817B2
公开(公告)日：2017-01-24
申请号：US14219642
申请日：2014-03-19
申请人： Microsoft Technology Licensing, LLC
发明人： Shuangyu Chang , Michael Levit , Abhik Lahiri , Barlas Oguz , Benoit Dumoulin
IPC分类号： G10L19/005 , G10L15/32
CPC分类号： G10L15/32 , G10L15/063 , G10L15/14 , G10L19/005
摘要： An incremental speech recognition system. The incremental speech recognition system incrementally decodes a spoken utterance using an additional utterance decoder only when the additional utterance decoder is likely to add significant benefit to the combined result. The available utterance decoders are ordered in a series based on accuracy, performance, diversity, and other factors. A recognition management engine coordinates decoding of the spoken utterance by the series of utterance decoders, combines the decoded utterances, and determines whether additional processing is likely to significantly improve the recognition result. If so, the recognition management engine engages the next utterance decoder and the cycle continues. If the accuracy cannot be significantly improved, the result is accepted and decoding stops. Accordingly, a decoded utterance with accuracy approaching the maximum for the series is obtained without decoding the spoken utterance using all utterance decoders in the series, thereby minimizing resource usage.
摘要翻译：增量语音识别系统。只有当附加话语解码器可能对组合结果增加显着的益处时，增量语音识别系统才会使用附加话音解码器递增地解码语音话语。可用的话语解码器是基于准确性，性能，多样性等因素进行排序的。识别管理引擎通过一系列话音解码器来协调语音发音的解码，组合解码的话语，并确定附加处理是否可能显着提高识别结果。如果是这样，识别管理引擎接合下一个话音解码器，并且该周期继续。如果精度无法显着提高，结果被接受，解码停止。因此，在使用系列中的所有话语解码器对语音发音进行解码的情况下，获得具有接近该系列的最大值的精确解码语音，从而最小化资源使用。

7. 发明申请

US20160253989A1 SPEECH RECOGNITION ERROR DIAGNOSIS 有权
标题翻译：语音识别错误诊断
公开(公告)号：US20160253989A1
公开(公告)日：2016-09-01
申请号：US14634714
申请日：2015-02-27
申请人： Microsoft Technology Licensing, LLC
发明人： Shiun-Zu Kuo , Thomas Reutter , Yifan Gong , Mark T. Hanson , Ye Tian , Shuangyu Chang , Jon Hamaker , Qi Miao , Yuancheng Tu
IPC分类号： G10L15/01 , G10L15/26 , G10L15/19
CPC分类号： G10L15/01 , G10L15/183
摘要： Techniques and technologies for diagnosing speech recognition errors are described. In an example implementation, a system for diagnosing speech recognition errors may include an error detection module configured to determine that a speech recognition result is least partially erroneous, and a recognition error diagnostics module. The recognition error diagnostics module may be configured to (a) perform a first error analysis of the at least partially erroneous speech recognition result to provide a first error analysis result; (b) perform a second error analysis of the at least partially erroneous speech recognition result to provide a second error analysis result; and (c) determine at least one category of recognition error associated with the at least partially erroneous speech recognition result based on a combination of the first error analysis result and the second error analysis result.
摘要翻译：描述用于诊断语音识别错误的技术和技术。在示例实现中，用于诊断语音识别错误的系统可以包括被配置为确定语音识别结果是最小部分错误的错误检测模块，以及识别错误诊断模块。识别错误诊断模块可以被配置为（a）对所述至少部分错误的语音识别结果执行第一误差分析以提供第一误差分析结果; （b）对所述至少部分错误的语音识别结果进行第二误差分析以提供第二误差分析结果; 以及（c）基于所述第一误差分析结果和所述第二误差分析结果的组合来确定与所述至少部分错误的语音识别结果相关联的至少一类识别错误。

8. 发明授权

US11636854B2 Meeting-adapted language model for speech recognition 有权
公开(公告)号：US11636854B2
公开(公告)日：2023-04-25
申请号：US17752623
申请日：2022-05-24
申请人： MICROSOFT TECHNOLOGY LICENSING, LLC
发明人： Ziad Al Bawab , Anand U Desai , Shuangyu Chang , Amit K Agarwal , Zoltan Romocsa , Christopher H Basoglu , Nathan E Wohlgemuth
IPC分类号： G10L15/193 , G06Q10/10 , G10L15/197 , G10L15/22 , G10L15/30 , G06Q10/107 , G06Q10/1093
摘要： A system includes acquisition of meeting data associated with a meeting, determination of a plurality of meeting participants based on the acquired meeting data, acquisition of e-mail data associated with each of the plurality of meeting participants, generation of a meeting language model based on the acquired e-mail data and the meeting data, and transcription of audio associated with the meeting based on the meeting language model.

9. 发明授权

US11120788B2 Organizational-based language model generation 有权
公开(公告)号：US11120788B2
公开(公告)日：2021-09-14
申请号：US16454621
申请日：2019-06-27
申请人： Microsoft Technology Licensing, LLC
发明人： Ziad Al Bawab , Anand U Desai , Cem Aksoylar , Michael Levit , Xin Meng , Shuangyu Chang , Suyash Choudhury , Dhiresh Rawal , Tao Li , Rishi Girish , Marcus Jager , Ananth Rampura Sheshagiri Rao
IPC分类号： G10L15/06 , G06N20/00 , G10L15/14 , G10L15/183
摘要： Provided is a system and method for acquiring training data and building an organizational-based language model based on the training data. In one example, the method may include collecting organizational data that is generated via one or more applications associated with an organization, aggregating the collected organizational data with previously collected organizational data to generate aggregated organizational training data, training an organizational-based language model for speech processing based on the aggregated organizational training data, and storing the trained organizational-based language model.

10. 发明授权

US09734826B2 Token-level interpolation for class-based language models 有权
公开(公告)号：US09734826B2
公开(公告)日：2017-08-15
申请号：US14644976
申请日：2015-03-11
申请人： Microsoft Technology Licensing, LLC
发明人： Michael Levit , Sarangarajan Parthasarathy , Andreas Stolcke , Shuangyu Chang
IPC分类号： G10L15/00 , G10L15/183 , G10L15/06 , G10L15/197 , G10L15/18
CPC分类号： G10L15/183 , G10L15/063 , G10L15/1815 , G10L15/197
摘要： Optimized language models are provided for in-domain applications through an iterative, joint-modeling approach that interpolates a language model (LM) from a number of component LMs according to interpolation weights optimized for a target domain. The component LMs may include class-based LMs, and the interpolation may be context-specific or context-independent. Through iterative processes, the component LMs may be interpolated and used to express training material as alternative representations or parses of tokens. Posterior probabilities may be determined for these parses and used for determining new (or updated) interpolation weights for the LM components, such that a combination or interpolation of component LMs is further optimized for the domain. The component LMs may be merged, according to the optimized weights, into a single, combined LM, for deployment in an application scenario.

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