METHOD OF AND SYSTEM FOR IMPROVING ACCURACY IN A SPEECH RECOGNITION SYSTEM
    1.
    发明申请
    METHOD OF AND SYSTEM FOR IMPROVING ACCURACY IN A SPEECH RECOGNITION SYSTEM 审中-公开
    用于提高语音识别系统中精度的方法和系统

    公开(公告)号:WO0211121A8

    公开(公告)日:2002-06-20

    申请号:PCT/US0123965

    申请日:2001-07-31

    Applicant: ELIZA CORP

    CPC classification number: G10L15/22

    Abstract: A method for transcribing an audio response including constructing an application including a plurality of queries and a set of textual formed responses for each query, posing each of the queries to a respondent, receiving an audio response to each query, performing a speech recognition function, recording each audio response, and comparing each textual response to the set of expected responses for each corresponding query (fig 2).

    Abstract translation: 一种用于转录音频响应的方法,包括构建包括多个查询的应用和针对每个查询的一组文本形成的响应,将每个查询构成为响应者,接收对每个查询的音频响应,执行语音识别功能, 记录每个音频响应,以及将每个文本响应与每个相应查询的预期响应的集合进行比较(图2)。

    METHOD OF AND SYSTEM FOR IMPROVING ACCURACY IN A SPEECH RECOGNITION SYSTEM

    公开(公告)号:CA2417926A1

    公开(公告)日:2002-02-07

    申请号:CA2417926

    申请日:2001-07-31

    Applicant: ELIZA CORP

    Abstract: A method for transcribing an audio response including constructing an application including a plurality of queries and a set of textual formed responses for each query, posing each of the queries to a respondent, receiving an audio response to each query, performing a speech recognition function, recording each audio response, and comparing each textual response to the set of expected responses for each corresponding query (fig 2).

    METHOD OF AND SYSTEM FOR IMPROVING ACCURACY IN A SPEECH RECOGNITION SYSTEM

    公开(公告)号:CA2417926C

    公开(公告)日:2013-02-12

    申请号:CA2417926

    申请日:2001-07-31

    Applicant: ELIZA CORP

    Abstract: A method for transcribing an audio response including constructing an application including a plurality of queries and a set of textual formed responses for each query, posing each of the queries to a respondent, receiving an audio response to each query, performing a speech recognition function, recording each audio response, and comparing each textual response to the set of expected responses for each corresponding query (fig 2).

Patent Agency Ranking