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

US10923105B2 Conversion of text-to-speech pronunciation outputs to hyperarticulated vowels 有权
公开(公告)号：US10923105B2
公开(公告)日：2021-02-16
申请号：US16204270
申请日：2018-11-29
申请人： Microsoft Technology Licensing, LLC
发明人： Kevin Chad Larson , Tanya Matskewich , Gregory Carl Hitchcock , Michael Tholfsen , Guillaume Simonnet , Viktoryia Akulich , Nicholas Kibre , Christina Chen Campbell
IPC分类号： G10L13/10 , G10L13/06 , G09B19/04 , G09B19/06 , G10L13/08
摘要： In non-limiting examples of the present disclosure, systems, methods and devices for mapping hyperarticulated sounds to text units are presented. A plurality of textual units may be received. The plurality of textual units may be processed with a natural language processing engine. A sentence structure for the plurality of textual units may be identified, wherein the sentence structure comprises a plurality of words. The plurality of words may be processed with a text-to-speech engine. A text-to-speech output comprising a plurality of pronunciations may be identified, wherein each of the plurality of pronunciations corresponds to a syllabic unit of one of the plurality of words. A hyperarticulated vowel sound may be mapped to each syllabic unit from the text-to-speech output. A pronunciation instruction corresponding to each hyperarticulated vowel sound may be caused to be surfaced.

2. 发明授权

US09589562B2 Pronunciation learning through correction logs 有权
标题翻译：发音通过校正日志学习
公开(公告)号：US09589562B2
公开(公告)日：2017-03-07
申请号：US14186476
申请日：2014-02-21
申请人： Microsoft Technology Licensing, LLC
发明人： Nicholas Kibre , Umut Ozertem , Sarangarajan Parthasarathy , Ziad Al Bawab
IPC分类号： G10L15/06 , G10L15/18 , G10L15/187 , G10L15/07 , G10L15/22
CPC分类号： G10L15/187 , G10L15/01 , G10L15/075 , G10L2015/025 , G10L2015/225
摘要： A new pronunciation learning system for dynamically learning new pronunciations assisted by user correction logs. The user correction logs provide a record of speech recognition events and subsequent user behavior that implicitly confirms or rejects the recognition result and/or shows the user's intended words by via subsequent input. The system analyzes the correction logs and distills them down to a set of words which lack acceptable pronunciations. Hypothetical pronunciations, constrained by spelling and other linguistic knowledge, are generated for each of the words. Offline recognition determines the hypothetical pronunciations with a good acoustical match to the audio data likely to contain the words. The matching pronunciations are aggregated and adjudicated to select new pronunciations for the words to improve general or personalized recognition models.
摘要翻译：一种用于动态学习由用户校正日志辅助的新发音的新发音学习系统。用户校正日志提供语音识别事件和后续用户行为的记录，其隐含地确认或拒绝识别结果和/或通过后续输入显示用户的预期词语。系统对校正日志进行分析，并将其解释为一组缺乏可接受发音的单词。为每个单词生成假说发音，受到拼写和其他语言知识的约束。离线识别确定具有与可能包含单词的音频数据良好声学匹配的假设发音。匹配的发音被聚合和裁决，以选择新的发音来改善一般或个性化的识别模型。

3. 发明申请

US20170154623A1 PRONUNCIATION LEARNING THROUGH CORRECTION LOGS 有权
公开(公告)号：US20170154623A1
公开(公告)日：2017-06-01
申请号：US15431350
申请日：2017-02-13
申请人： Microsoft Technology Licensing, LLC.
发明人： Nicholas Kibre , Umut Ozertem , Sarangarajan Parthasarathy , Ziad Al Bawab
IPC分类号： G10L15/187 , G10L15/07
CPC分类号： G10L15/187 , G10L15/01 , G10L15/075 , G10L2015/025 , G10L2015/225
摘要： A new pronunciation learning system for dynamically learning new pronunciations assisted by user correction logs. The user correction logs provide a record of speech recognition events and subsequent user behavior that implicitly confirms or rejects the recognition result and/or shows the user's intended words by via subsequent input. The system analyzes the correction logs and distills them down to a set of words which lack acceptable pronunciations. Hypothetical pronunciations, constrained by spelling and other linguistic knowledge, are generated for each of the words. Offline recognition determines the hypothetical pronunciations with a good acoustical match to the audio data likely to contain the words. The matching pronunciations are aggregated and adjudicated to select new pronunciations for the words to improve general or personalized recognition models.

4. 发明授权

US09947317B2 Pronunciation learning through correction logs 有权
公开(公告)号：US09947317B2
公开(公告)日：2018-04-17
申请号：US15431350
申请日：2017-02-13
申请人： Microsoft Technology Licensing, LLC
发明人： Nicholas Kibre , Umut Ozertem , Sarangarajan Parthasarathy , Ziad Al Bawab
IPC分类号： G10L15/187 , G10L15/07 , G10L15/01 , G10L15/02
CPC分类号： G10L15/187 , G10L15/01 , G10L15/075 , G10L2015/025 , G10L2015/225
摘要： A new pronunciation learning system for dynamically learning new pronunciations assisted by user correction logs. The user correction logs provide a record of speech recognition events and subsequent user behavior that implicitly confirms or rejects the recognition result and/or shows the user's intended words by via subsequent input. The system analyzes the correction logs and distills them down to a set of words which lack acceptable pronunciations. Hypothetical pronunciations, constrained by spelling and other linguistic knowledge, are generated for each of the words. Offline recognition determines the hypothetical pronunciations with a good acoustical match to the audio data likely to contain the words. The matching pronunciations are aggregated and adjudicated to select new pronunciations for the words to improve general or personalized recognition models.

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