利索-全球专利检索

  1. 登录
  2. 注册

搜索结果

32 条记录 (耗时 0.019 秒)

    System and method for accessing TV-related information over the internet
    2.
    发明公开
    System and method for accessing TV-related information over the internet 审中-公开
    通过互联网访问电视相关信息的系统和方法

    公开(公告)号：EP1094406A2

    公开(公告)日：2001-04-25

    申请号：EP00306964.8

    申请日：2000-08-15

    申请人： Matsushita Electric Industrial Co., Ltd.

    发明人： Kuhn, Roland ,  Junqua, Jean-Claude ,  Davis, Tony ,  Li, Weiying ,  Zhao, Yi

    IPC分类号： G06F17/30

    CPC分类号： G06F17/30663 ,  G10L2015/228

    摘要： The system retrieves information from the internet using multiple search engines that are simultaneously launched by the search engine commander. The commander is responsive to a speech-enabled system including a speech recognizer and natural language parser. The user speaks to the system in natural language requests, and the parser extracts the semantic content from the user's speech, based on a set of goal oriented grammars. The preferred system includes a fixed grammar and an updatable or downloaded grammar, allowing the system to be used without extensive training and yet capable of being customized for a particular user's purposes. Results obtained from the search engines are filtered based on information extracted from an electronic program guide and from prestored user profile data. The results may be displayed on screen or through synthesized speech.

    摘要翻译： 该系统使用由搜索引擎指挥官同时发起的多个搜索引擎从互联网获取信息。 指挥官对包括语音识别器和自然语言分析器在内的支持语音的系统作出响应。 用户以自然语言请求向系统讲话，并且解析器基于一组面向目标的语法从用户语音中提取语义内容。 优选的系统包括固定语法和可更新或下载的语法，允许系统在没有广泛培训的情况下使用，并且能够针对特定用户的目的进行定制。 基于从电子节目指南中提取的信息和从预先存储的用户简档数据中过滤搜索引擎获得的结果。 结果可以显示在屏幕上或通过合成语音。

    Speaker and environment adaptation based on eigenvoices including maximum likelihood method
    3.
    发明公开
    Speaker and environment adaptation based on eigenvoices including maximum likelihood method 有权
    基于语音特征值和最大似然法扬声器和环境适应

    公开(公告)号：EP0953968A2

    公开(公告)日：1999-11-03

    申请号：EP99303417.2

    申请日：1999-04-30

    申请人： MATSUSHITA ELECTRIC INDUSTRIAL CO., LTD.

    发明人： Nguyen, Patrick ,  Kuhn, Roland ,  Junqua, Jean-Claude

    IPC分类号： G10L3/00

    CPC分类号： G06K9/6247 ,  G10L15/07

    摘要： A set of speaker dependent models is trained upon a comparatively large number of training speakers, one model per speaker, and model parameters are extracted in a predefined order to construct a set of supervectors, one per speaker. Principle component analysis is then performed on the set of supervectors to generate a set of eigenvectors that define an eigenvoice space. If desired, the number of vectors may be reduced to achieve data compression. Thereafter, a new speaker provides adaptation data from which a supervector is constructed by constraining this supervector to be in the eigenvoice space based on a maximum likelihood estimation. The resulting coefficients in the eigenspace of this new speaker may then be used to construct a new set of model parameters from which an adapted model is constructed for that speaker. Environmental adaptation may be performed by including environmental variations in the training data.

    摘要翻译： 一组说话者相关模型的在比较大的数目的扬声器的锻炼训练，每一个扬声器模型和模型参数在预定义的顺序来构造一组超向量，每个说话者一个的提取。 然后主成分分析进行该组超向量以生成一组特征向量并限定到固有声音的空间。 如果需要清除，矢量的数量可以被减小，以实现数据压缩。 那里以后，新的发言者的适应会提供一个超级矢量通过约束这个超级矢量是基于最大似然估计的奇特声音的空间构造的数据。 在这个新的扬声器的特殊步伐最终的系数可以被用来构建了一套新的从模型参数angepasst模型构建了该扬声器。 环境的适应也可以进行通过在锻炼数据环境的变化。

    System for identifying and adapting a TV-user profile by means of speech technology
    7.
    发明公开
    System for identifying and adapting a TV-user profile by means of speech technology 审中-公开
    System zur Identifizierung und Anpassung des Profiles eines Fernsehbenutzer mittels Sprachtechnologie

    公开(公告)号：EP1079615A2

    公开(公告)日：2001-02-28

    申请号：EP00307289.9

    申请日：2000-08-24

    申请人： MATSUSHITA ELECTRIC INDUSTRIAL CO., LTD.

    发明人： Junqua, Jean-Claude ,  Kuhn, Roland ,  Davis, Tony ,  Li, Weiying ,  Zhao, Yi

    IPC分类号： H04N5/44

    CPC分类号： H04N21/4532 ,  G10L17/00 ,  H04N5/44543 ,  H04N21/42203 ,  H04N21/4227 ,  H04N21/43615 ,  H04N21/4415 ,  H04N21/47 ,  H04N21/654

    摘要： Speech input supplied by the user is evaluated by the speaker verification/identification module, and based on the evaluation, parameters are retrieved from a user profile database. These parameters adapt the speech models of the speech recognizer and also supply the natural language parser with customized dialog grammars. The user's speech is then interpreted by the speech recognizer and natural language parser to determine the meaning of the user's spoken input in order to control the television tuner. The parser works in conjunction with a command module that mediates the dialog with the user, providing on-screen prompts or synthesized speech queries to elicit further input from the user when needed. The system integrates with an electronic program guide, so that the natural language parser is made aware of what programs are available when conducting the synthetic dialog with the user. Speech can be input through either a microphone or over the telephone. In addition, the user can interact with the system using a suitable computer attached via the Internet. Regardless of the mode of access, the unified access controller interprets the semantic content of the user's request and supplies the appropriate control signals to the television tuner and/or recorder.

    摘要翻译： 由用户提供的语音输入由说话人验证/识别模块进行评估，并且基于评估，从用户简档数据库检索参数。 这些参数适应语音识别器的语音模型，并为自然语言解析器提供定制的对话语法。 用户的语音然后由语音识别器和自然语言解析器来解释，以确定用户的口头输入的含义，以控制电视调谐器。 解析器与一个命令模块一起工作，该模块与用户调停对话，提供屏幕上的提示或合成语音查询，以便在需要时从用户中引出进一步的输入。 该系统与电子节目指南集成，使得自然语言解析器在与用户进行合成对话时就意识到可用的程序。 语音可以通过麦克风或通过电话输入。 此外，用户可以使用通过因特网连接的合适的计算机与系统交互。 无论访问方式如何，统一访问控制器解释用户请求的语义内容，并将适当的控制信号提供给电视调谐器和/或记录器。

    Mechanism for storing information about recorded television broadcasts
    8.
    发明公开
    Mechanism for storing information about recorded television broadcasts 审中-公开
    Vorrichtung zum Speichern von Informationenüberaufgezeichnete Fernsehsendungen

    公开(公告)号：EP1079387A2

    公开(公告)日：2001-02-28

    申请号：EP00306974.7

    申请日：2000-08-15

    申请人： Matsushita Electric Industrial Co., Ltd.

    发明人： Junqua, Jean-Claude ,  Kuhn, Roland ,  Davis, Tony ,  Li, Weiying ,  Zhao, Yi

    IPC分类号： G11B27/00 ,  G11B27/11 ,  G06F17/30

    CPC分类号： G06F17/30017 ,  G11B27/002 ,  G11B27/034 ,  G11B27/105 ,  G11B27/107 ,  G11B27/11 ,  G11B27/327 ,  G11B27/34 ,  G11B27/36 ,  G11B2220/20 ,  G11B2220/41 ,  H04N5/44543 ,  H04N21/42203 ,  H04N21/4325 ,  H04N21/4332 ,  H04N21/4335 ,  H04N21/4394 ,  H04N21/44222 ,  H04N21/482 ,  H04N21/84

    摘要： Program content, recorded to a storage medium such as disk recorder, optical recorder or random access memory, is indexed by the replay file system. The file system maintains a storage location and program I.D. record for each recorded program. The file system further maintains other data obtained from an electronic program guide that may be accessed by downloading from the cable or satellite infrastructure or over the internet. The file system also may store additional user data, such as the date and time the program was last viewed, together with any user-recorded indexes. The file system may be accessed through natural language input speech. The system includes a speech recognizer and natural language parser, coupled to a dialog system that engages the user in a dialog to determine what the user is interested in accessing from the storage medium. The natural language parser operates with a task-based grammar that is keyed to the electronic program guide data and user data maintained by the file system.

    摘要翻译： 记录到诸如磁盘记录器，光学记录器或随机存取存储器之类的存储介质的程序内容被重放文件系统索引。 文件系统维护一个存储位置和程序I.D. 记录每个记录的程序。 文件系统进一步维护从电子节目指南获得的其他数据，该数据可以通过从有线或卫星基础设施或互联网下载而被访问。 文件系统还可以存储附加用户数据，例如上次查看程序的日期和时间以及任何用户记录的索引。 文件系统可以通过自然语言输入语音访问。 该系统包括语音识别器和自然语言解析器，耦合到对话系统，该对话系统使用户在对话中接合以确定用户对存储介质的访问感兴趣。 自然语言解析器与基于任务的语法一起操作，该语法被键入电子节目指南数据和由文件系统维护的用户数据。

    Voice activated controller for recording and retrieving audio/video programs
    9.
    发明公开
    Voice activated controller for recording and retrieving audio/video programs 审中-公开
    通过语音操作控制组记录和音频/视频节目检索

    公开(公告)号：EP1037463A2

    公开(公告)日：2000-09-20

    申请号：EP00301825.6

    申请日：2000-03-06

    申请人： Matsushita Electric Industrial Co., Ltd.

    发明人： Contolini, Matteo ,  Junqua, Jean-Claude ,  Kuhn, Roland

    IPC分类号： H04N5/782

    CPC分类号： H04N21/440236 ,  G10L2015/223 ,  G11B27/002 ,  G11B27/105 ,  G11B27/107 ,  G11B27/11 ,  G11B27/34 ,  G11B27/36 ,  G11B2220/2516 ,  G11B2220/2545 ,  G11B2220/2562 ,  G11B2220/41 ,  G11B2220/455 ,  G11B2220/65 ,  G11B2220/90 ,  H04N5/781 ,  H04N5/782 ,  H04N5/85 ,  H04N21/42203 ,  H04N21/4334 ,  H04N21/47214 ,  H04N21/84 ,  H04N21/8405

    摘要： A speech understanding system (16) for receiving a spoken request from a user (12) and processing the request against a multimedia database of audio/visual (A/V) programming information (20) for automatically recording and/or retrieving an A/V program is disclosed. The system includes a database (20) of program records representing A/V programs which are available for recording. The system also includes an A/V recording device (40-42) for receiving a recording command and recording the A/\/ program. A speech recognizer (48) is provided for receiving the spoken request and translating the spoken request into a text stream having a plurality of words. A natural language processor (50) receives the text stream and processes the words for resolving a semantic content of the spoken request. The natural language processor (50) places the meaning of the words into a task frame (90) having a plurality of key word slots (92-98). A dialogue system (60) analyzes the task frame (90) for determining if a sufficient number of key word slots (92-98) have been filled and prompts the user for additional information for filling empty slots. The dialogue system (60) searches the database of program records (20) using the key words placed within the task frame (90) for selecting the A/V program and generating the recording command for use by the A/V recording device (40-42).

    摘要翻译： 一种语音理解系统（16），用于从用户（12）接收所说的请求并处理对音频/视频（A / V）编程信息（20）的多媒体数据库中请求用于自动地记录和/或A的检索/ V节目是游离缺失盘。 该系统包括表示A / V节目哪些是可用于记录程序记录的数据库（20）。 因此，该系统包括：A / V记录设备（40-42），用于接收记录命令和记录在A / E /程序。 语音识别器（48）被设置用于接收所述口头请求和翻译口头请求转换成具有字的多元性的文本流。 自然语言处理器（50）接收文本流和处理的话用于解决口头请求的语义内容。 自然语言处理器（50）放置的词的含义为具有键字槽（92-98）的多个A任务帧（90）。 对话系统（60）分析如果键字槽（92-98）的足够数量的被填充用于确定性采矿任务框架（90），并提示用于填充空槽附加信息的用户。 对话系统（60）检索的程序记录使用用于选择A / V节目和用于由所述A / V记录设备使用产生的记录命令的任务框架（90）内放置的关键词（在数据库（20）40 -42）。