Speech recognition using multiple language models
    2.
    发明授权
    Speech recognition using multiple language models 有权
    多语言模型的语音识别

    公开(公告)号:US08972260B2

    公开(公告)日:2015-03-03

    申请号:US13450861

    申请日:2012-04-19

    摘要: In accordance with one embodiment, a method of generating language models for speech recognition includes identifying a plurality of utterances in training data corresponding to speech, generating a frequency count of each utterance in the plurality of utterances, generating a high-frequency plurality of utterances from the plurality of utterances having a frequency that exceeds a predetermined frequency threshold, generating a low-frequency plurality of utterances from the plurality of utterances having a frequency that is below the predetermined frequency threshold, generating a grammar-based language model using the high-frequency plurality of utterances as training data, and generating a statistical language model using the low-frequency plurality of utterances as training data.

    摘要翻译: 根据一个实施例,一种生成用于语音识别的语言模型的方法包括:识别与语音相对应的训练数据中的多个话语,产生多个话语中的每个发声的频率计数,从多个话语中产生高频多个话语 所述多个话音具有超过预定频率阈值的频率,从具有低于所述预定频率阈值的频率的所述多个话语中产生低频多个话语,使用所述高频率生成基于语法的语言模型 多个话语作为训练数据,并且使用低频多个话语生成统计语言模型作为训练数据。

    SPEECH RECOGNITION USING MULTIPLE LANGUAGE MODELS
    3.
    发明申请
    SPEECH RECOGNITION USING MULTIPLE LANGUAGE MODELS 有权
    使用多种语言模型进行语音识别

    公开(公告)号:US20120271631A1

    公开(公告)日:2012-10-25

    申请号:US13450861

    申请日:2012-04-19

    IPC分类号: G10L15/06

    摘要: In accordance with one embodiment, a method of generating language models for speech recognition includes identifying a plurality of utterances in training data corresponding to speech, generating a frequency count of each utterance in the plurality of utterances, generating a high-frequency plurality of utterances from the plurality of utterances having a frequency that exceeds a predetermined frequency threshold, generating a low-frequency plurality of utterances from the plurality of utterances having a frequency that is below the predetermined frequency threshold, generating a grammar-based language model using the high-frequency plurality of utterances as training data, and generating a statistical language model using the low-frequency plurality of utterances as training data.

    摘要翻译: 根据一个实施例,一种生成用于语音识别的语言模型的方法包括:识别与语音相对应的训练数据中的多个话语,产生多个话语中的每个发声的频率计数,从多个话语中产生高频多个话语 所述多个话音具有超过预定频率阈值的频率,从具有低于所述预定频率阈值的频率的所述多个话语中产生低频多个话语,使用所述高频率生成基于语法的语言模型 多个话语作为训练数据,并且使用低频多个话语生成统计语言模型作为训练数据。

    Method and apparatus for providing proper or partial proper name recognition
    8.
    发明申请
    Method and apparatus for providing proper or partial proper name recognition 有权
    提供正确或部分正确名称识别的方法和装置

    公开(公告)号:US20060015484A1

    公开(公告)日:2006-01-19

    申请号:US10892724

    申请日:2004-07-15

    申请人: Fuliang Weng Lin Zhao

    发明人: Fuliang Weng Lin Zhao

    IPC分类号: G06F17/30 G06F17/27 G06F7/00

    CPC分类号: G06F17/278

    摘要: A method of proper name recognition includes classifying each word of a word string with a tag indicating a proper name entity category or a non-named entity category, and correcting the tag of a boundary word of the word string.

    摘要翻译: 正确名称识别的方法包括用指示正确名称实体类别或非命名实体类别的标签对单词串的每个单词进行分类,以及校正字串的边界字的标签。

    Method and apparatus for providing proper or partial proper name recognition
    9.
    发明授权
    Method and apparatus for providing proper or partial proper name recognition 有权
    提供正确或部分正确名称识别的方法和装置

    公开(公告)号:US07865356B2

    公开(公告)日:2011-01-04

    申请号:US10892724

    申请日:2004-07-15

    申请人: Fuliang Weng Lin Zhao

    发明人: Fuliang Weng Lin Zhao

    IPC分类号: G06F17/27

    CPC分类号: G06F17/278

    摘要: A method of proper name recognition includes classifying each word of a word string with a tag indicating a proper name entity category or a non-named entity category, and correcting the tag of a boundary word of the word string.

    摘要翻译: 正确名称识别的方法包括用指示正确名称实体类别或非命名实体类别的标签对单词串的每个单词进行分类,以及校正字串的边界字的标签。

    Statistical applications in OLTP environment
    10.
    发明授权
    Statistical applications in OLTP environment 有权
    OLTP环境中的统计应用

    公开(公告)号:US08862539B2

    公开(公告)日:2014-10-14

    申请号:US13610395

    申请日:2012-09-11

    申请人: Lin Zhao

    发明人: Lin Zhao

    IPC分类号: G06F17/30

    摘要: The present disclosure provides a method of statistical application in an OLTP environment to reduce the intensive computational load of invoking SQL statements for statistical calculations. The method introduces a time element into statistical records, and use the time element to determine the time status of previously computed statistical records. Upon receiving a query for a statistical record, the system first searches for an existing copy of the statistical record, and checks the time status of the statistical record if found. The system sends the statistical record to the inquirer if the record exists and is unexpired, and invokes an SQL statement to compute the statistical record only if the record does not exist or has expired. The statistical records may be placed in statistical table in a database and/or a cache of an application server. The disclosed strategy may also increase attack resistance of the system.

    摘要翻译: 本公开提供了在OLTP环境中的统计应用的方法,以减少用于统计计算的调用SQL语句的密集计算负载。 该方法将时间元素引入统计记录,并使用time元素来确定先前计算的统计记录的时间状态。 在收到统计记录的查询后,系统首先搜索统计记录的现有副本,并检查统计记录的时间状态。 如果记录存在并且未过期,系统将统计记录发送给查询者,并且只有在记录不存在或已过期时才调用SQL语句来计算统计记录。 统计记录可以放置在应用服务器的数据库和/或缓存中的统计表中。 所公开的策略还可以增加系统的攻击阻力。