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. 发明申请

US20170287465A1 Speech Recognition and Text-to-Speech Learning System 审中-公开
公开(公告)号：US20170287465A1
公开(公告)日：2017-10-05
申请号：US15087696
申请日：2016-03-31
申请人： Microsoft Technology Licensing, LLC
发明人： Pei Zhao , Kaisheng Yao , Max Leung , Bo Yan
IPC分类号： G10L13/10 , G10L15/06 , G10L13/08
CPC分类号： G10L13/10 , G10L13/08 , G10L13/086 , G10L15/063 , G10L15/07
摘要： An example text-to-speech learning system performs a method for generating a pronunciation sequence conversion model. The method includes generating a first pronunciation sequence from a speech input of a training pair and generating a second pronunciation sequence from a text input of the training pair. The method also includes determining a pronunciation sequence difference between the first pronunciation sequence and the second pronunciation sequence; and generating a pronunciation sequence conversion model based on the pronunciation sequence difference. An example speech recognition learning system performs a method for generating a pronunciation sequence conversion model. The method includes extracting an audio signal vector from a speech input and applying an audio signal conversion model to the audio signal vector to generate a converted audio signal vector. The method also includes adapting an acoustic model based on the converted audio signal vector to generate an adapted acoustic model.

2. 发明授权

US11238842B2 Intent recognition and emotional text-to-speech learning 有权
公开(公告)号：US11238842B2
公开(公告)日：2022-02-01
申请号：US16309399
申请日：2017-06-07
申请人： MICROSOFT TECHNOLOGY LICENSING, LLC
发明人： Pei Zhao , Kaisheng Yao , Max Leung , Bo Yan , Jian Luan , Yu Shi , Malone Ma , Mei-Yuh Hwang
IPC分类号： G10L15/18 , G10L13/027 , G06F3/16 , G10L13/08 , G10L15/06 , G10L15/22 , G10L15/26 , G10L25/63
摘要： An example intent-recognition system comprises a processor and memory storing instructions. The instructions cause the processor to receive speech input comprising spoken words. The instructions cause the processor to generate text results based on the speech input and generate acoustic feature annotations based on the speech input. The instructions also cause the processor to apply an intent model to the text result and the acoustic feature annotations to recognize an intent based on the speech input. An example system for adapting an emotional text-to-speech model comprises a processor and memory. The memory stores instructions that cause the processor to receive training examples comprising speech input and receive labelling data comprising emotion information associated with the speech input. The instructions also cause the processor to extract audio signal vectors from the training examples and generate an emotion-adapted voice font model based on the audio signal vectors and the labelling data.

3. 发明授权

US10127901B2 Hyper-structure recurrent neural networks for text-to-speech 有权
公开(公告)号：US10127901B2
公开(公告)日：2018-11-13
申请号：US14303969
申请日：2014-06-13
申请人： Microsoft Technology Licensing, LLC
发明人： Pei Zhao , Max Leung , Kaisheng Yao , Bo Yan , Sheng Zhao , Fileno A. Alleva
IPC分类号： G10L13/10 , G06N3/02 , G10L13/08 , G06N3/04
摘要： The technology relates to converting text to speech utilizing recurrent neural networks (RNNs). The recurrent neural networks may be implemented as multiple modules for determining properties of the text. In embodiments, a part-of-speech RNN module, letter-to-sound RNN module, a linguistic prosody tagger RNN module, and a context awareness and semantic mining RNN module may all be utilized. The properties from the RNN modules are processed by a hyper-structure RNN module that determine the phonetic properties of the input text based on the outputs of the other RNN modules. The hyper-structure RNN module may generate a generation sequence that is capable of being converting to audible speech by a speech synthesizer. The generation sequence may also be optimized by a global optimization module prior to being synthesized into audible speech.

4. 发明授权

US11727914B2 Intent recognition and emotional text-to-speech learning 有权
公开(公告)号：US11727914B2
公开(公告)日：2023-08-15
申请号：US17561895
申请日：2021-12-24
申请人： MICROSOFT TECHNOLOGY LICENSING, LLC
发明人： Pei Zhao , Kaisheng Yao , Max Leung , Bo Yan , Jian Luan , Yu Shi , Malone Ma , Mei-Yuh Hwang
IPC分类号： G10L13/027 , G06F3/16 , G10L13/08 , G10L15/06 , G10L15/18 , G10L15/22 , G10L15/26 , G10L25/63
CPC分类号： G10L13/027 , G06F3/167 , G10L13/08 , G10L15/063 , G10L15/1807 , G10L15/22 , G10L15/26 , G10L25/63 , G10L2015/223
摘要： An example intent-recognition system comprises a processor and memory storing instructions. The instructions cause the processor to receive speech input comprising spoken words. The instructions cause the processor to generate text results based on the speech input and generate acoustic feature annotations based on the speech input. The instructions also cause the processor to apply an intent model to the text result and the acoustic feature annotations to recognize an intent based on the speech input. An example system for adapting an emotional text-to-speech model comprises a processor and memory. The memory stores instructions that cause the processor to receive training examples comprising speech input and receive labelling data comprising emotion information associated with the speech input. The instructions also cause the processor to extract audio signal vectors from the training examples and generate an emotion-adapted voice font model based on the audio signal vectors and the labelling data.

5. 发明授权

US10089974B2 Speech recognition and text-to-speech learning system 有权
公开(公告)号：US10089974B2
公开(公告)日：2018-10-02
申请号：US15087696
申请日：2016-03-31
申请人： Microsoft Technology Licensing, LLC
发明人： Pei Zhao , Kaisheng Yao , Max Leung , Bo Yan
IPC分类号： G10L13/00 , G10L13/10 , G10L13/08 , G10L15/06
摘要： An example text-to-speech learning system performs a method for generating a pronunciation sequence conversion model. The method includes generating a first pronunciation sequence from a speech input of a training pair and generating a second pronunciation sequence from a text input of the training pair. The method also includes determining a pronunciation sequence difference between the first pronunciation sequence and the second pronunciation sequence; and generating a pronunciation sequence conversion model based on the pronunciation sequence difference. An example speech recognition learning system performs a method for generating a pronunciation sequence conversion model. The method includes extracting an audio signal vector from a speech input and applying an audio signal conversion model to the audio signal vector to generate a converted audio signal vector. The method also includes adapting an acoustic model based on the converted audio signal vector to generate an adapted acoustic model.

6. 发明授权

US09293129B2 Speech recognition assisted evaluation on text-to-speech pronunciation issue detection 有权
标题翻译：语音识别辅助评估文本到语音发音问题检测
公开(公告)号：US09293129B2
公开(公告)日：2016-03-22
申请号：US13785573
申请日：2013-03-05
申请人： Microsoft Technology Licensing, LLC
发明人： Pei Zhao , Bo Yan , Lei He , Zhe Geng , Yiu-Ming Leung
IPC分类号： G10L13/08
CPC分类号： G10L13/086 , G10L13/08
摘要： Pronunciation issues for synthesized speech are automatically detected using human recordings as a reference within a Speech Recognition Assisted Evaluation (SRAE) framework including a Text-To-Speech flow and a Speech Recognition (SR) flow. A pronunciation issue detector evaluates results obtained at multiple levels of the TTS flow and the SR flow (e.g. phone, word, and signal level) by using the corresponding human recordings as the reference for the synthesized speech, and outputs possible pronunciation issues. A signal level may be used to determine similarities/differences between the recordings and the TTS output. A model level checker may provide results to the pronunciation issue detector to check the similarities of the TTS and the SR phone set including mapping relations. Results from a comparison of the SR output and the recordings may also be evaluation by the pronunciation issue detector. The pronunciation issue detector outputs a list that lists potential pronunciation issue candidates.
摘要翻译：在语音识别辅助评估（SRAE）框架内使用人类录音作为参考，自动检测合成语音的发音问题，包括文本到语音流和语音识别（SR）流。发音问题检测器通过使用相应的人类记录作为合成语音的参考来评估在多个级别的TTS流和SR流（例如电话，字和信号电平）上获得的结果，并输出可能的发音问题。可以使用信号电平来确定记录和TTS输出之间的相似/差异。模型级检查器可以向发音问题检测器提供结果，以检查包括映射关系的TTS和SR电话机的相似性。通过比较SR输出和记录的结果也可以由发音问题检测器进行评估。发音问题检测器输出列出潜在发音问题候选人的列表。

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