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

EP1670194B8 Service guarantee and congestion control in high speed networks 失效
标题翻译：高速网络中的服务保证和拥塞控制
公开(公告)号：EP1670194B8
公开(公告)日：2013-04-17
申请号：EP06111782.6
申请日：1993-06-28
申请人： AT&T Intellectual Property II, L.P.
发明人： Cole, Robert G , Fendick, Kerry W. , Rodrigues, Manoel A.
IPC分类号： H04Q11/04
CPC分类号： H04L12/5602 , H04L12/66 , H04L47/10 , H04L47/12 , H04L47/16 , H04L47/29 , H04L47/30 , H04L47/32 , H04L2012/5636

2. 发明授权

EP1168299B8 Method and system for preselection of suitable units for concatenative speech 有权
标题翻译：方法和系统，用于级联合成预选有利的语音段
公开(公告)号：EP1168299B8
公开(公告)日：2013-03-13
申请号：EP01305403.6
申请日：2001-06-21
申请人： AT&T Intellectual Property II, L.P.
发明人： Conkie, Alistair D.
IPC分类号： G10L13/06
CPC分类号： G10L13/07 , G10L2015/022
摘要： A system and method for improving the response time of text-to-speech synthesis utilizes "triphone contexts" (i.e., triplets comprising a central phoneme and its immediate context) as the basic unit, instead of performing phoneme-by-phoneme synthesis. Prior to initiating the "real time" synthesis, a database is created of all possible triphones (there are approximately 10000 in the English language) and their associated preselection costs. At run time, therefore, only the most likely candidates are selected from the triphone database, significantly reducing the calculations that are required to be performed in real time.

3. 发明授权

EP1696421B1 Learning in automatic speech recognition 有权转让
标题翻译：学习语音识别
公开(公告)号：EP1696421B1
公开(公告)日：2008-08-20
申请号：EP06110328.9
申请日：2006-02-23
申请人： AT&T Corp.
发明人： Hakkani-Tur, Dilek Z. , Rahim, Mazin G. , Tur, Gokhan , Riccardi, Giuseppe
IPC分类号： G10L15/06
CPC分类号： G10L15/063 , G10L15/07 , G10L15/18 , G10L15/26 , G10L2015/0638

4. 发明授权

EP1696524B1 Fast dynamic gain control in an optical fiber amplifier 有权
标题翻译：在光纤放大器快动态增益控制
公开(公告)号：EP1696524B1
公开(公告)日：2014-04-02
申请号：EP06101460.1
申请日：2006-02-09
申请人： AT&T Intellectual Property II, L.P.
发明人： ZHOU, Xiang , BIRK, Martin
IPC分类号： H01S3/094 , H01S3/00 , H01S3/067 , H01S3/131 , H01S3/30
CPC分类号： H01S3/302 , H01S3/005 , H01S3/06758 , H01S3/06766 , H01S3/0677 , H01S3/094003 , H01S3/094096 , H01S3/10015 , H01S3/1301 , H01S2301/04

5. 发明授权

EP0888025B1 Method and apparatus for providing partitioned telecommunication service 失效
标题翻译：对于电信服务分开的供给方法及装置
公开(公告)号：EP0888025B1
公开(公告)日：2014-01-01
申请号：EP98304671.5
申请日：1998-06-12
申请人： AT&T Intellectual Property II, L.P.
发明人： Amin, Umesh J.
IPC分类号： H04W8/02 , H04W48/18 , H04W84/14
CPC分类号： H04W48/18 , H04W8/02 , H04W84/14

6. 发明授权

EP0719062B1 Method and system of delivering a variety of broadband/narrowband services 失效
标题翻译：方法和系统提供多种基础广泛/窄带业务
公开(公告)号：EP0719062B1
公开(公告)日：2013-05-15
申请号：EP95308755.8
申请日：1995-12-05
申请人： AT&T Intellectual Property II, L.P.
发明人： Rudrapatna, Ashok N. , Jaisingh, Gopal K. , Miller II, Robert R. , Russell, Jesse E. , Schroeder, Robert E.
IPC分类号： H04B7/185 , H04W4/00 , H04Q11/04
CPC分类号： H04W4/00 , H04B7/18578 , H04L2012/5607 , H04L2012/5608 , H04L2012/5616 , H04Q11/0435 , H04Q11/0478 , H04Q2213/13332 , H04W28/18 , H04W74/02 , H04W88/04 , H04W88/06 , Y10S370/907

7. 发明授权

EP1331797B1 Communication system for hearing-impaired persons comprising speech to text conversion terminal 有权转让
标题翻译：用于与语音/文本转换单元听力受损的通信系统
公开(公告)号：EP1331797B1
公开(公告)日：2008-12-10
申请号：EP03100036.7
申请日：2003-01-10
申请人： AT&T Corp.
发明人： CALDWELL, Charles, David , HARLOW, John, Bruce , SAYKO, Robert , SHAYE, Norman
IPC分类号： H04M1/247 , H04N7/173
CPC分类号： H04M1/2475 , H04M1/2535 , H04M1/57 , H04M11/066 , H04N21/4394 , H04N21/440236 , H04N21/4788

8. 发明公开

EP1696421A2 Learning in automatic speech recognition 有权转让
标题翻译： Lernen zur Spracherkennung
公开(公告)号：EP1696421A2
公开(公告)日：2006-08-30
申请号：EP06110328.9
申请日：2006-02-23
申请人： AT&T Corp.
发明人： Hakkani-Tur, Dilek Z. , Rahim, Mazin G. , Tur, Gokhan , Riccardi, Giuseppe
IPC分类号： G10L15/06
CPC分类号： G10L15/063 , G10L15/07 , G10L15/18 , G10L15/26 , G10L2015/0638
摘要： Utterance data that includes at least a small amount of manually transcribed data is provided. Automatic speech recognition is performed on ones of the utterance data not having a corresponding manual transcription to produce automatically transcribed utterances. A model is trained using all of the manually transcribed data and the automatically transcribed utterances. A predetermined number of utterances not having a corresponding manual transcription are intelligently selected and manually transcribed. Ones of the automatically transcribed data as well as ones having a corresponding manual transcription are labeled. In another aspect of the invention, audio data is mined from at least one source, and a language model is trained for call classification from the mined audio data to produce a language model.
摘要翻译：提供了包括至少少量手动转录数据的语音数据。对没有相应的手动转录的话语数据中的一个执行自动语音识别以产生自动转录的话语。使用所有手动转录数据和自动转录的话语训练模型。智能地选择并手动转录预定数量的不具有相应手动转录的话语。自动转录的数据以及具有相应手动转录的数据的标签。在本发明的另一方面，音频数据从至少一个源开始，并且语言模型被训练用于从所开采的音频数据进行呼叫分类以产生语言模型。

9. 发明授权

EP1170724B8 Synthesis-based pre-selection of suitable units for concatenative speech 有权
标题翻译：对于拼接合成有利的语段代码
公开(公告)号：EP1170724B8
公开(公告)日：2013-03-13
申请号：EP01305404.4
申请日：2001-06-21
申请人： AT&T Intellectual Property II, L.P.
发明人： Conkie, Alistair D.
IPC分类号： G10L13/06
CPC分类号： G10L13/07
摘要： A method and system for providing concatenative speech uses a speech synthesis input to populate a triphone-indexed database that is later used for searching and retrieval to create a phoneme string acceptable for a text-to-speech operation. Prior to initiating the "real time" synthesis, a database is created of all possible triphone contexts by inputting a continuous stream of speech. The speech data is then analyzed to identify all possible triphone sequences in the stream, and the various units chosen for each context. During a later text-to-speech operation, the triphone contexts in the text are identified and the triphone-indexed phonemes in the database are searched to retrieve the best-matched candidates.

10. 发明公开

EP1696421A3 Learning in automatic speech recognition 有权转让
标题翻译：学习语音识别
公开(公告)号：EP1696421A3
公开(公告)日：2007-02-28
申请号：EP06110328.9
申请日：2006-02-23
申请人： AT&T Corp.
发明人： Hakkani-Tur, Dilek Z. , Rahim, Mazin G. , Tur, Gokhan , Riccardi, Giuseppe
IPC分类号： G10L15/06
CPC分类号： G10L15/063 , G10L15/07 , G10L15/18 , G10L15/26 , G10L2015/0638
摘要： Utterance data that includes at least a small amount of manually transcribed data is provided. Automatic speech recognition is performed on ones of the utterance data not having a corresponding manual transcription to produce automatically transcribed utterances. A model is trained using all of the manually transcribed data and the automatically transcribed utterances. A predetermined number of utterances not having a corresponding manual transcription are intelligently selected and manually transcribed. Ones of the automatically transcribed data as well as ones having a corresponding manual transcription are labeled. In another aspect of the invention, audio data is mined from at least one source, and a language model is trained for call classification from the mined audio data to produce a language model.

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