专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

71. 发明公开

EP2590393A4 SERVICE SERVER DEVICE, SERVICE PROVISION METHOD, AND SERVICE PROVISION PROGRAM 审中-公开
标题翻译：服务设备，服务处理和服务程序
公开(公告)号：EP2590393A4
公开(公告)日：2014-01-08
申请号：EP12789828
申请日：2012-05-24
申请人： NTT DOCOMO INC
发明人： NASU KAZUNORI , SHIBATA SEIJI , AKUZAWA MARI , UCHIYAMA KEN
IPC分类号： G06F17/28 , G10L15/06 , G10L15/26 , H04M3/42
CPC分类号： G06F17/28 , G06F17/289 , G10L15/26 , G10L15/30 , G10L2015/0638 , G10L2015/221 , H04M3/42 , H04M3/42221 , H04M2201/39 , H04M2201/40 , H04M2201/60 , H04M2203/2061

72. 发明公开

EP2596492A1 EFFICIENTLY REDUCING TRANSCRIPTION ERROR USING HYBRID VOICE TRANSCRIPTION 有权
标题翻译： ABSCHREIBENFEHLERN有效卸载使用混合语言转录
公开(公告)号：EP2596492A1
公开(公告)日：2013-05-29
申请号：EP11734235.2
申请日：2011-07-13
申请人： Intellisist Inc.
发明人： MILSTEIN, David
IPC分类号： G10L15/06
CPC分类号： G10L15/26 , G10L15/01 , G10L15/06 , G10L15/063 , G10L15/10 , G10L15/1822 , G10L15/19 , G10L15/22 , G10L2015/0631 , G10L2015/0638 , H04M3/42221 , H04M3/51 , H04M3/5183
摘要： A system and method for efficiently reducing transcription error using hybrid voice transcription is provided. A voice stream is parsed from a call into utterances. An initial transcribed value and corresponding recognition score are assigned to each utterance. A transcribed message is generated for the call and includes the initial transcribed values. A threshold is applied to the recognition scores to identify those utterances with recognition scores below the threshold as questionable utterances. At least one questionable utterance is compared to other questionable utterances from other calls and a group of similar questionable utterances is formed. One or more of the similar questionable utterances is selected from the group. A common manual transcription value is received for the selected similar questionable utterances. The common manual transcription value is assigned to the remaining similar questionable utterances in the group.

73. 发明公开

EP2399251A4 TEACHING AID 审中-公开
标题翻译：教具
公开(公告)号：EP2399251A4
公开(公告)日：2013-04-24
申请号：EP10743329
申请日：2010-02-19
申请人： UNICUS INVEST PTY LTD
发明人： KING PETER LAWRENCE
IPC分类号： G09B5/04 , G09B5/06 , G09B17/00 , G10L13/00
CPC分类号： G10L15/22 , G09B17/006 , G10L2015/0638

74. 发明公开

EP1606793A4 SPEECH RECOGNITION METHOD 审中-公开
标题翻译：语音识别过程
公开(公告)号：EP1606793A4
公开(公告)日：2007-05-16
申请号：EP03800389
申请日：2003-12-31
申请人： LESSAC TECHNOLOGY INC , WILSON DONALD H , HANDAL ANTHONY H , LESSAC MICHAEL LESSAC TECHNOLO
发明人： WILSON DONALD H , HANDAL ANTHONY H , LESSAC MICHAEL
IPC分类号： G09B5/04 , G09B19/04 , G09B21/00 , G10L13/08 , G10L15/04 , G10L15/06 , G10L15/18
CPC分类号： G10L13/10 , G09B5/04 , G09B19/04 , G09B21/00 , G10L15/063 , G10L15/187 , G10L2015/0638
摘要： In accordance with a present invention speech recognition is disclosed (10). It uses a microphone to receive audible sounds input by a user into a first computing device (28) having a program with a database (16) comprising (i) digital responses of known audible sounds and associated alphanumeric representations of the known audible sounds and for the first time (ii) digital representations of known audible sounds corresponding to mispronunciations resulting from known class of mispronounced words and phrases. The method is performed by receiving the audible sounds in the form of the electrical output of the microphone (28). A particular audible sound to be recognized is converted into a digital representation of the audible sound (30). The digital representation of the particular audible sound is then compared to the digital representations of the known audible sounds to determine which of those known audible sounds is most likely to be the particular audible sounds in the database (30).

75. 发明授权

EP1072297B1 Information processing apparatus 有权
标题翻译：一种信息处理设备
公开(公告)号：EP1072297B1
公开(公告)日：2007-04-25
申请号：EP99961362.3
申请日：1999-12-24
申请人： SONY CORPORATION
发明人： Fujimura, Satoshi, Sony Corporation , Yokoo, Naohiro, Sony Corporation , Kato, Yasuhiko, Sony Corporation
IPC分类号： A63F13/00 , A63F13/10 , A63F13/12 , G10L13/00 , G10L15/00 , G10L17/00 , G06F17/20 , G06F9/44 , G10L15/26 , G06F15/18 , G06N3/00 , G06F19/00
CPC分类号： G06N3/008 , A63F13/12 , A63F13/424 , A63F13/71 , A63F13/825 , A63F2300/1081 , A63F2300/204 , A63F2300/402 , A63F2300/65 , A63F2300/8058 , G06N3/006 , G10L13/00 , G10L13/027 , G10L15/063 , G10L15/26 , G10L2015/0638

76. 发明公开

EP1758351A2 Method and system for enrolling addresses in a speech recognition database 失效
标题翻译：系统和Verfahren zur Aufnahme von Namen在einer Spracherkennungsdatenbank
公开(公告)号：EP1758351A2
公开(公告)日：2007-02-28
申请号：EP06022529.9
申请日：1996-09-12
申请人： TEXAS INSTRUMENTS INCORPORATED
发明人： Gammel, Michele B. , Fisher, Thomas D.
IPC分类号： H04M1/27
CPC分类号： G10L15/063 , G10L15/20 , G10L2015/0638 , H04M1/271
摘要： A method and system for enrolling speed dial names includes providing speaker dependent templates and associated telephone numbers and providing a penalized garbage model for unrecognized speech. When a request for a new template is received it is determined if the list of speed dial names is full (Step 201) and is not it is determined if that name is too similar (Step 205) to a name already on the speed dial list. If so, that name is rejected but if not it is determined if the speed dial name is too short (Step 302), and if not too short or if the user wants to enter the short name the system asks the user to repeat the speed dial name and if a match it is entered. If not a match the system will swap the first and second utterance and compare to see if a match.
摘要翻译：用于登记快速拨号名称的方法和系统包括提供说话者依赖模板和相关联的电话号码，并为未被识别的语音提供惩罚垃圾模型。当接收到对新模板的请求时，确定快速拨号名称的列表是否已满（步骤201），并且不确定该名称是否与已经在快速拨号列表上的名称太相似（步骤205）。如果是，该名称被拒绝，但如果不是确定快速拨号名称是否太短（步骤302），如果不是太短，或者如果用户想要输入短名称，则系统要求用户重复速度拨打名称并输入匹配项。如果不匹配，系统会交换第一个和第二个发音，并比较一下是否匹配。

77. 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.

78. 发明授权

EP0762709B1 Method and system for enrolling addresses in a speech recognition database 失效
标题翻译：系统和方法在语音识别数据库名称记录
公开(公告)号：EP0762709B1
公开(公告)日：2006-11-29
申请号：EP96306624.6
申请日：1996-09-12
申请人： TEXAS INSTRUMENTS INCORPORATED
发明人： Gammel, Michele B. , Fisher, Thomas D.
IPC分类号： H04M1/27
CPC分类号： G10L15/063 , G10L15/20 , G10L2015/0638 , H04M1/271

79. 发明公开

EP1701337A2 Method of setting posterior probability parameters for a switching state space model and method of speech recognition 有权
标题翻译：设置切换状态空间模型和语音识别方法的后验概率参数的方法
公开(公告)号：EP1701337A2
公开(公告)日：2006-09-13
申请号：EP06013383.2
申请日：2005-01-13
申请人： Microsoft Corporation
发明人： Attias, Hagai , Lee, Leo , Deng, Li
IPC分类号： G10L15/14
CPC分类号： G10L15/14 , G10L2015/0638
摘要： A method of efficiently setting posterior probability parameters for a switching state space model begins by defining a window containing at least two but fewer than all of the frames. A separate posterior probability parameter is determined for each frame in the window. The window is then shifted sequentially from left to right in time so that it includes one or more subsequent frames in the sequence of frames. A separate posterior probability parameter is then determined for each frame in the shifted window. This method closely approximates a more rigorous solution but saves computational cost by two to three orders of magnitude. Further, a method of determining the optimal discrete state sequence in the switching state space model is invented that directly exploits the observation vector on a frame-by-frame basis and operates from left to right in time.
摘要翻译：有效地设置切换状态空间模型的后验概率参数的方法首先定义包含至少两个但少于全部帧的窗口。为窗口中的每个帧确定单独的后验概率参数。该窗口然后在时间上从左向右依次移位，以便它包括帧序列中的一个或多个后续帧。然后为移位窗口中的每个帧确定单独的后验概率参数。这种方法非常接近更严格的解决方案，但节省了两到三个数量级的计算成本。此外，发明了一种在开关状态空间模型中确定最佳离散状态序列的方法，该方法在逐帧的基础上直接利用观测向量，并且按时间从左向右操作。

80. 发明公开

EP1557823A2 Method of setting posterior probability parameters for a switching state space model and method of speech recognition 有权
标题翻译：一种用于概率参数的确定为状态空间模型变量方法
公开(公告)号：EP1557823A2
公开(公告)日：2005-07-27
申请号：EP05000586.7
申请日：2005-01-13
申请人： MICROSOFT CORPORATION
发明人： Attias, Hagai , Lee, Leo , Deng, Li
IPC分类号： G10L15/14
CPC分类号： G10L15/14 , G10L2015/0638
摘要： A method of efficiently setting posterior probability parameters for a switching state space model begins by defining a window containing at least two but fewer than all of the frames. A separate posterior probability parameter is determined for each frame in the window. The window is then shifted sequentially from left to right in time so that it includes one or more subsequent frames in the sequence of frames. A separate posterior probability parameter is then determined for each frame in the shifted window. This method closely approximates a more rigorous solution but saves computational cost by two to three orders of magnitude. Further, a method of determining the optimal discrete state sequence in the switching state space model is invented that directly exploits the observation vector on a frame-by-frame basis and operates from left to right in time.
摘要翻译：用于切换状态空间模型设定高效后验概率参数的方法开始于定义含有至少两个但不是全部的帧的较少的窗口。一个单独的后验概率参数确定性开采窗口中的每个帧。窗，然后在时间上移位顺序地从左至右所以做到了包括帧序列中的一个或多个随后的帧。一个单独的后验概率的参数，然后确定开采在移位窗口中的每个帧。这种方法非常接近更严格的解决方案，但节省了两到三个数量级的计算成本。另外，在开关状态空间模型的最优离散状态序列发明确定性采矿的方法做了直接利用上一帧接一帧的基础上观测矢量和从在时间从左向右运行。

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