专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

11. 发明申请

WO2005101708A2 METHOD FOR STORING BROADCAST CONTENTS, AND A BROADCAST CONTENT STORAGE SYSTEM 审中-公开
标题翻译：存储广播内容的方法和广播内容存储系统
公开(公告)号：WO2005101708A2
公开(公告)日：2005-10-27
申请号：PCT/IB2005051125
申请日：2005-04-06
申请人： PHILIPS INTELLECTUAL PROPERTY , KONINKL PHILIPS ELECTRONICS NV , THELEN ERIC , KLAKOW DIETRICH
发明人： THELEN ERIC , KLAKOW DIETRICH
IPC分类号： H04H60/27 , H04H60/47 , H04H60/73 , H04N5/76 , H04N5/781 , H04N5/782 , H04H9/00 , H04H1/00
CPC分类号： H04H60/73 , G11B27/034 , G11B27/105 , G11B2220/2516 , H04H60/27 , H04H60/47 , H04N5/781 , H04N5/782
摘要： The invention describes a method for storing broadcast contents and a broadcast content storage system. A plurality of content categories (KAT1, KAT2) is pre-defined, each of which is defined or described by at least one content descriptor (OB 1, OB2). Broadcast contents transmitted over at least one broadcast transmission channel are received, preferably continually, or over pre-defined lengths of time. Received broadcast contents, which are described by a content descriptor (OB1, OB2), are automatically assigned to the content category (KAT1, KAT2) defined or described by the corresponding content descriptor (OB1, OB2). The broadcast contents assigned to a content category (KAT1, KAT2) and the assignments of the broadcast contents to the corresponding content categories (KAT1, KAT2) are automatically stored.
摘要翻译：本发明描述了一种用于存储广播内容的方法和广播内容存储系统。多个内容类别（KAT1，KAT2）被预定义，每个内容类别由至少一个内容描述符（OB 1，OB 2）定义或描述。通过至少一个广播传输信道发送的广播内容优选地连续地或超过预定义的时间长度被接收。由内容描述符（OB1，OB2）描述的接收的广播内容被自动分配给由对应的内容描述符（OB1，OB2）定义或描述的内容类别（KAT1，KAT2）。自动存储分配给内容类别（KAT1，KAT2）的广播内容和广播内容对相应内容类别（KAT1，KAT2）的分配。

12. 发明申请

WO0054251A3 METHOD OF SPEECH RECOGNITION 审中-公开
标题翻译：语音识别方法
公开(公告)号：WO0054251A3
公开(公告)日：2000-12-28
申请号：PCT/EP0001143
申请日：2000-02-10
申请人： KONINKL PHILIPS ELECTRONICS NV , PHILIPS CORP INTELLECTUAL PTY
发明人： BESLING STEFAN , THELEN ERIC , ULLRICH MEINHARD
IPC分类号： G06F3/16 , G10L15/00 , G10L15/26 , G10L15/28
CPC分类号： G10L15/26
摘要： In a method in which an information unit (4) enabling a speech input is stored on a server (5) and can be retrieved by a client (1, 2, 3) and in which the client can be coupled to one or more speech recognizers (7, 8, 9) through a communications network (6), the information unit (4) is assigned additional information (12) which is provided for determining a combination of a client (1, 2, 3) for recognizing an uttered speech signal and at least one of the speech recognizers (7, 8, 9), to dynamically assign the speech recognizers (7, 8, 9) in a communications network (6) to the information units (4) and thus ensure an acceptable processing time for the recognition of a speech input with a high recognition quality.
摘要翻译：在使得能够进行语音输入的信息单元（4）被存储在服务器（5）上并且可以由客户端（1,2,3）被检索并且客户端可以耦合到一个或多个语音的方法中识别器（7,8,9）通过通信网络（6），信息单元（4）被分配附加信息（12），其被提供用于确定用于识别发送的客户端（1,2,3）的组合语音信号和所述语音识别器（7,8,9）中的至少一个，以将通信网络（6）中的语音识别器（7,8,9）动态地分配给信息单元（4），从而确保可接受的用于识别具有高识别质量的语音输入的处理时间。

13. 发明申请

WO9918556A3 VOCABULARY AND/OR LANGUAGE MODEL TRAINING 审中-公开
标题翻译：词汇和/或语言模式培训
公开(公告)号：WO9918556A3
公开(公告)日：1999-06-24
申请号：PCT/IB9801421
申请日：1998-09-14
申请人： KONINKL PHILIPS ELECTRONICS NV , PHILIPS PATENTVERWALTUNG , PHILIPS SVENSKA AB
发明人： THELEN ERIC , BESLING STEFAN , DEJARNETT STEVE
IPC分类号： G06F17/28 , G09B1/00 , G09B19/06 , G10L15/18 , G10L3/00
CPC分类号： G09B19/06 , Y10S707/99933 , Y10S707/99934 , Y10S707/99936
摘要： A system (300) comprising means (310) for creating a vocabulary and/or statistical language model (330) from a textual training corpus. The vocabulary and/or language model are used in a pattern recognition system (350), such as a speech recognition system or a handwriting recognition system, for recognising a time-sequential input pattern (352). The system (300) comprises means (335) for determining at least one context identifier and means (332) for deriving at least one search criterion, such as a keyword, from the context identifier. The system further comprises means (334) for selecting documents from a set of documents based on the search criterion. Advantageously, an Internet search engine is used for selecting the documents. Means (336) are used for composing the training corpus from the selected documents.
摘要翻译：一种包括用于从文本训练语料库创建词汇和/或统计语言模型（330）的装置（310）的系统（300）。词汇和/或语言模型用于模式识别系统（350），例如语音识别系统或手写识别系统，用于识别时间顺序输入模式（352）。系统（300）包括用于确定至少一个上下文标识符的装置（335）和用于从上下文标识符导出诸如关键字的至少一个搜索准则的装置（332）。该系统还包括用于基于搜索标准从一组文档中选择文档的装置（334）。有利地，使用因特网搜索引擎来选择文档。装置（336）用于从所选文档组成训练语料库。

14. 发明申请

WO0058942A3 CLIENT-SERVER SPEECH RECOGNITION 审中-公开
标题翻译：客户服务器语音识别
公开(公告)号：WO0058942A3
公开(公告)日：2001-01-11
申请号：PCT/EP0001977
申请日：2000-03-07
申请人： KONINKL PHILIPS ELECTRONICS NV , PHILIPS CORP INTELLECTUAL PTY
发明人： THELEN ERIC , BESLING STEFAN
IPC分类号： G06F3/16 , G10L15/14 , G10L15/26 , G10L15/30
CPC分类号： G10L15/30 , G10L15/26
摘要： A distributed speech recognition system (300) includes at least one client station (330) and a server station (310) connected via a network (350), such as Internet. The client station (330) includes means (331) for receiving the speech input signal from a user. A speech controller (335) directs at least part of the speech input signal to a local speech recognizer (334). The, preferably limited, speech recognizer (334) is capable of recognizing at least part of the speech input, for instance a spoken command for starting full recognition. In dependence on the outcome of the recognition, the speech controller (335) selectively directs a part of the speech input signal via the network (350) to the server station (310). The server station (310) includes means (312) for receiving the speech equivalent signal from the network and a large/huge vocabulary speech recognizer (314) for recognizing the received speech equivalent signal.
摘要翻译：分布式语音识别系统（300）包括经由诸如因特网的网络（350）连接的至少一个客户站（330）和服务器站（310）。客户站（330）包括用于从用户接收语音输入信号的装置（331）。语音控制器（335）将至少部分语音输入信号引导到本地语音识别器（334）。优选有限的语音识别器（334）能够识别语音输入的至少一部分，例如用于开始完全识别的口语命令。根据识别的结果，语音控制器（335）经由网络（350）有选择地将语音输入信号的一部分引导到服务器站（310）。服务器站（310）包括用于从网络接收语音等效信号的装置（312）和用于识别接收到的语音等效信号的大/巨大词汇语音识别器（314）。

15. 发明申请

WO0054252A2 METHOD WITH A PLURALITY OF SPEECH RECOGNIZERS 审中-公开
标题翻译：具有多个语音识别器的方法
公开(公告)号：WO0054252A2
公开(公告)日：2000-09-14
申请号：PCT/EP0001145
申请日：2000-02-10
申请人： KONINKL PHILIPS ELECTRONICS NV , PHILIPS CORP INTELLECTUAL PTY
发明人： ULLRICH MEINHARD , THELEN ERIC , BESLING STEFAN
IPC分类号： G06F3/16 , G10L15/32 , G10L
CPC分类号： G10L15/32
摘要： The invention relates to a method in which an information unit (3) that makes a speech input possible is stored on a server (1) and can be retrieved by a client (2) and the client (2) can be coupled through the communications network (6) to a plurality of speech recognizers (7-9) and a speech input given by a user is applied to at least one speech recognizer (7-9) for generating at least one recognition result (11-13) and the recognition result (11-13) is interpreted in a plurality of independent processes and a plurality of interpretation results (22-24) are generated which are sent to a user. The user then receives in a brief period of time a plurality of qualified information items for which otherwise he would several times have had to make an inquiry in databases by means of a speech input.
摘要翻译：本发明涉及一种方法，其中使得能够进行语音输入的信息单元（3）被存储在服务器（1）上并且可以被客户端（2）检索并且客户端（2）可以通过通信网络（6）连接到多个语音识别器（7-9），并且由用户给出的语音输入被应用到至少一个语音识别器（7-9）以产生至少一个识别结果（11-13），并且所述识别结果（11-13）在多个独立处理中被解释，并且生成发送给用户的多个解释结果（22-24）。然后，用户在短时间内接收多个合格的信息项目，否则他将多次必须通过语音输入在数据库中进行查询。

16. 发明申请

WO9921172A2 PATTERN RECOGNITION ENROLMENT IN A DISTRIBUTED SYSTEM 审中-公开
标题翻译：分布式系统中的模式识别注入
公开(公告)号：WO9921172A2
公开(公告)日：1999-04-29
申请号：PCT/IB9801566
申请日：1998-10-08
申请人： KONINKL PHILIPS ELECTRONICS NV , PHILIPS SVENSKA AB
发明人： BESLING STEFAN , THELEN ERIC
IPC分类号： G10L15/06 , G06K9/62 , G10L15/00 , G10L15/10 , G10L15/26 , G10L15/28 , G10L15/30 , G10L15/34 , G10L5/06
CPC分类号： G10L15/34 , G06K9/6217 , G10L15/30
摘要： A distributed pattern recognition system (300) comprises at least one user station (350) and a server station (310). The server station (310) and the user station (350) are connected via a network (330), such as Internet. The server station (310) comprises different recognition models of a same type. As part of a recognition enrolment, the user station (350) transfers model improvement data associated with a user of the user station (350) to the server station (310). The server station (310) selects a recognition model from the different recognition models of a same type in dependence on the model improvement data. For each recognition session, the user station (350) transfers an input pattern representative of time sequential input generated by the user to the server station (310). The server station (310) retrieves a recognition model selected for the user and provides the retrieved recognition model to a recognition unit (322) for recognising the input pattern using the recognition models.
摘要翻译：分布式模式识别系统（300）包括至少一个用户站（350）和服务器站（310）。服务器站（310）和用户站（350）经由诸如因特网的网络（330）连接。服务器站（310）包括相同类型的不同识别模型。作为识别登记的一部分，用户站（350）将与用户站（350）的用户相关联的模型改进数据传送到服务器站（310）。服务器站（310）根据模型改进数据从相同类型的不同识别模型中选择识别模型。对于每个识别会话，用户站（350）将表示由用户生成的时间顺序输入的输入模式传送到服务器站（310）。服务器站（310）检索为用户选择的识别模型，并将检索到的识别模型提供给识别单元（322），以使用识别模型来识别输入模式。

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