Method and device for recognizing speech
    1.
    发明授权
    Method and device for recognizing speech 有权
    用于识别语音的方法和设备

    公开(公告)号:US09514738B2

    公开(公告)日:2016-12-06

    申请号:US14442191

    申请日:2012-11-13

    Inventor: Yoichi Ando

    Abstract: A speech is recognized using ACF factors extracted from running autocorrelation functions calculated from the speech. The extracted ACF factors are a Wφ(0) (width of ACF amplitude around zero-delay origin), a Wφ(0)max (maximum value of the Wφ(0)), a τ1 (pitch period), a φ1 (pitch strength), and a Δφ1/Δt (rate of the pitch strength change). Syllables in the speech are identified by comparing the ACF factors with templates stored in a database.

    Abstract translation: 使用从语音计算的运行自相关函数中提取的ACF因子识别语音。 提取的ACF因子是Wφ(0)(围绕零延迟原点的ACF幅度的宽度),Wφ(0)max(Wφ(0)的最大值),τ1(音调周期),φ1(音调 强度)和Δφ1/Δt(俯仰强度变化率)。 语音中的音节通过将ACF因子与存储在数据库中的模板进行比较来识别。

    METHOD AND DEVICE FOR RECOGNIZING SPEECH
    2.
    发明申请
    METHOD AND DEVICE FOR RECOGNIZING SPEECH 有权
    用于识别语音的方法和设备

    公开(公告)号:US20150348536A1

    公开(公告)日:2015-12-03

    申请号:US14442191

    申请日:2012-11-13

    Inventor: Yoichi ANDO

    Abstract: A speech is recognized using ACF factors extracted from running autocorrelation functions calculated from the speech. The extracted ACF factors are a Wφ(0) (width of ACF amplitude around zero-delay origin), a Wφ(0)max (maximum value of the Wφ(0)), a τ1 (pitch period), a φ1 (pitch strength), and a Δφ1/Δt (rate of the pitch strength change). Syllables in the speech are identified by comparing the ACF factors with templates stored in a database.

    Abstract translation: 使用从语音计算的运行自相关函数中提取的ACF因子识别语音。 提取的ACF因子是W(ph)(0)(零延迟起源的ACF幅度的宽度),W&phgr(0)max(W&phgr;(0)的最大值)),τ1(音调周期),a &phgr。1(俯仰强度),和&Dgr&&Grgr; 1 /&Dgr; t(俯仰强度变化率)。 语音中的音节通过将ACF因子与存储在数据库中的模板进行比较来识别。

Patent Agency Ranking