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. 发明公开

EP0954857A4 AUDIO-BASED WIDE AREA INFORMATION SYSTEM 失效
标题翻译：音频基础WEITBEREICHS-INFORMATIONSSYSTEM
公开(公告)号：EP0954857A4
公开(公告)日：2000-04-26
申请号：EP97952551
申请日：1997-12-16
申请人： TELCORDIA TECH INC
发明人： BARBARA DANIEL , NAQVI SHAMIN A
IPC分类号： G06F3/16 , G06F17/30 , G10L15/22 , G10L19/00 , H04H20/00 , H04M3/00 , H04M3/42 , H04M3/493 , G10L7/08 , H04M3/50
CPC分类号： G10L15/222 , G10L15/22 , G10L25/48
摘要： A wide area information system includes a client and at least one server on which audio data is stored. Audio data is selectively transferred to the client from the server by at least occasionally establishing a transfer connection between the server and the client. The transfer of audio data is controlled by user-selected commands and inputs that are entered via an input interface provided on the client. These commands and inputs are also transferred to the server via the at least occasionally established transfer connection between the client and the server. The audio data on the server is organized in page units that are cross-linked by way of hyperaudio links. The page units are characteristically searchable with the use of cyclically repeating directory pages of audible directory information. A data protocol is defined for enabling such an audio-based system.
摘要翻译：广域信息系统包括客户端和存储音频数据的至少一个服务器。通过至少偶尔在服务器和客户端之间建立传输连接，音频数据从服务器选择性地传送到客户端。音频数据的传输由用户选择的命令和通过客户端上提供的输入接口输入的输入来控制。这些命令和输入也通过客户端和服务器之间的至少偶尔建立的传输连接传送到服务器。服务器上的音频数据是以通过超音频链接交互的页面单元组织的。通过使用循环重复的可听目录信息的目录页，可以搜索页面单元。最后，定义了一种数据协议，用于启用这种基于音频的系统。

2. 发明授权

EP0624865B1 Arrangement for increasing the comprehension of speech when translating speech from a first language to a second language 失效
标题翻译：用于从第一语言提高语音的语言翻译可懂成第二布置
公开(公告)号：EP0624865B1
公开(公告)日：1999-09-15
申请号：EP94850070.7
申请日：1994-04-28
申请人： TELIA AB
发明人： Lyberg, Bertil
IPC分类号： G10L5/04 , G10L5/06 , G10L7/08 , G10L9/06
CPC分类号： G10L13/08

3. 发明授权

EP0626674B1 A method and apparatus for speech encoding, speech decoding and speech post processing 失效
标题翻译：对于语音编码和语音解码和Sprachnachverarbeitung方法和装置
公开(公告)号：EP0626674B1
公开(公告)日：1999-08-25
申请号：EP94106988.2
申请日：1994-05-04
申请人： MITSUBISHI DENKI KABUSHIKI KAISHA
发明人： Ishii, Jun
IPC分类号： G10L9/14 , G10L9/18 , G10L5/06 , G10L7/08
CPC分类号： G10L19/06 , G10L19/002 , G10L19/0212 , G10L19/24 , G10L19/26

4. 发明授权

EP0575033B1 Architecture for covariance matrix generation 失效
标题翻译：架构产生共变矩阵
公开(公告)号：EP0575033B1
公开(公告)日：1999-07-14
申请号：EP93302223.8
申请日：1993-03-24
申请人： ADVANCED MICRO DEVICES, INC.
发明人： Bartkowiak, John G. , Nix, Michael A.
IPC分类号： G06F17/16 , G10L5/06 , G10K15/02 , G10L7/08 , G10L9/06
CPC分类号： G06F17/16

5. 发明公开

EP0854468A3 Determinization and minimization for speech recognition 失效
标题翻译：语音识别的确定和最小化
公开(公告)号：EP0854468A3
公开(公告)日：1998-12-30
申请号：EP98300140.5
申请日：1998-01-09
申请人： AT&T Corp.
发明人： Mohri, Mehrya , Pereira, Fernando Carlos Neves , Riley, Michael Dennis
IPC分类号： G10L5/04 , G10L7/08 , G10L9/06 , G10L9/18
CPC分类号： G10L15/193
摘要： A pattern recognition system and method for optimal reduction of redundancy and size of a weighted and labeled graph presents receiving speech signals, converting the speech signals into word sequences, interpreting the word sequences in a graph where the graph is labeled with word sequences and weighted with probabilities and determinizing the graph by removing redundant word sequences. The size of the graph can also be minimized by collapsing some nodes of the graph in a reverse determinizing manner. The graph can further be tested for determinizability to determine if the graph can be determinized. The resulting word sequence in the graph may be shown in a display device so that recognition of speech signals can be demonstrated.
摘要翻译：用于最佳减少加权和标记图的冗余和大小的模式识别系统和方法呈现接收语音信号，将语音信号转换成单词序列，在图中解释单词序列，其中图用单词序列标记并且用概率并通过去除多余的单词序列来确定图形。图形的大小也可以通过以反向确定方式折叠图形的一些节点来最小化。可以进一步测试该图的可确定性以确定该图是否可以确定。图中得到的单词序列可以显示在显示设备中，以便可以演示语音信号的识别。

6. 发明公开

EP0851404A3 System and method for enhanced intelligibility of voice messages 失效
标题翻译：的设备和方法的语音消息的增强的清晰度
公开(公告)号：EP0851404A3
公开(公告)日：1998-12-30
申请号：EP97121959.7
申请日：1997-12-12
申请人： AT&T Corp.
发明人： Rochkind, Mark Meier
IPC分类号： G10L5/02 , G10L5/04 , G10L7/08 , G10L9/06 , G10L9/18
CPC分类号： H04M3/533 , G10L19/00 , G10L21/04 , H04M1/6505 , H04M1/652
摘要： A system and method is provided for playing back a recorded voice message, and, in particular, for automatically playing back a spoken numeric portion of the message at a rate that is slower than the rate for playing back the remaining portion of the recorded voice message. A voice messaging system receives and analyzes the voice message. Specifically, the messaging system determines whether the voice message includes spoken numeric information and, if so, determines the relative position of the spoken numeric information within the message. The computer system stores both the voice message and the positional information in a storage device. Upon playback of the message, the messaging system retrieves the stored voice message and positional information from the storage device. As the voice message is played back, the messaging system processes the positional information. When the positional information indicates that a particular portion of a voice message includes spoken numeric information, that particular portion is played back at a decreased speed.

7. 发明授权

EP0822538B1 Method of transforming periodic signal using smoothed spectrogram, method of transforming sound using phasing component and method of analyzing signal using optimum interpolation function 失效
标题翻译：一种用于将使用的扁平Spectrogrammes的周期性信号的方法，与使用相组分和方法用于使用最佳内插分析的信号的声音的转化方法
公开(公告)号：EP0822538B1
公开(公告)日：1998-12-30
申请号：EP97112087.8
申请日：1997-07-15
申请人： ATR HUMAN INFORMATION PROCESSING RESEARCH LABORATORIES
发明人： Kawahara, Hideki, c/o ATR Human Information , Masauda, Ikuyo, c/o ATR Human Information
IPC分类号： G10L3/02 , G10L5/06 , G10L7/08 , G10L9/06 , G10L9/18
CPC分类号： G10L25/48 , G10L21/04 , G10L2021/0135

8. 发明授权

EP0582312B1 Speech recognition apparatus 失效
标题翻译：用于语音识别
公开(公告)号：EP0582312B1
公开(公告)日：1998-12-09
申请号：EP93112661.9
申请日：1993-08-06
申请人： SEIKO EPSON CORPORATION
发明人： Inazumi, Mitsuhiro, c/o Seiko Epson Corporation
IPC分类号： G10L5/06 , G10L7/08 , G10L9/06
CPC分类号： G10L15/16

9. 发明公开

EP0834861A3 Verfahren zur Berechnung eines Schwellenwertes für die Spracherkennung eines Schlüsselwortes 失效
标题翻译：一种用于为关键字的语音识别来计算阈值的方法
公开(公告)号：EP0834861A3
公开(公告)日：1998-11-18
申请号：EP97115989.2
申请日：1997-09-12
申请人： SIEMENS AKTIENGESELLSCHAFT
发明人： Junkawitsch, Jochen , Höge, Harald , Ruske, Günther
IPC分类号： G10L5/06 , G10L7/08 , G10L9/06 , G10L9/18
CPC分类号： G10L15/142 , G10L2015/088
摘要： Mit der Erfindung wird ein Verfahren angegeben, womit wortindividuell Akzeptanzschwellenwerte für Schlüsselworte berechnet werden können. Das neue der Erfindung besteht darin, daß für diese Entscheidungsschwellen keine Wortdatenbanken der entsprechenden Schlüsselworte verfügbar sein müssen, da die Wahrscheinlichkeitsverteilungsdichten der Scores der entsprechenden Schlüsselworte völlig synthetisch berechnet werden. Dies geschieht dadurch, daß die jeweiligen Schlüsselworte in Phoneme zerlegt werden und die Wahrscheinlichkeitsverteilungen der Scores der Phoneme längengewichtet zu einer Wahrscheinlichkeitsverteilung für ein Schlüsselwort überlagert werden. Die Wahrscheinlichkeitsdichtefunktion dieser Linearkombination erhält man durch Faltung der skalierten Dichtefunktionen der einzelnen Phoneme. Das erfindungsgemäße Verfahren ist in den unterschiedlichsten Wordspotting-Systemen einsetzbar. Beispiele dafür sind sprachgesteuerte Maschinen.

10. 发明公开

EP0854469A3 Speech encoding apparatus and method 失效
公开(公告)号：EP0854469A3
公开(公告)日：1998-08-05
申请号：EP98105128.7
申请日：1994-05-04
申请人： MITSUBISHI DENKI KABUSHIKI KAISHA
发明人： Ishii, Jun
IPC分类号： G10L9/14 , G10L9/18 , G10L5/06 , G10L7/08
CPC分类号： G10L19/06 , G10L19/002 , G10L19/0212 , G10L19/24 , G10L19/26
摘要： A speech analysis means and a window locating means are implemented in a speech coding apparatus. The speech coding apparatus encodes input speech per analysis frame defined having a fixed length and is offset at fixed interval. The speech analysis means extracts frequency spectrum characteristic parameters of the input speech taken within an analysis window. The location of the analysis window is specified by the window locating means. The window locating means selects the location of the analysis window which is used in extracting the frequency spectrum characteristic parameters at the speech analysis means. In this case, depending upon the characteristic parameter of the input speech within and near the frame concerned, the window locating means selects the location of the analysis window within the range which is not to be exceeding the range of the frame concerned.

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