Method for facilitating text to speech synthesis using a differential vocoder
    1.
    发明申请
    Method for facilitating text to speech synthesis using a differential vocoder 审中-公开
    使用差分声码器促进文本到语音合成的方法

    公开(公告)号:US20070106513A1

    公开(公告)日:2007-05-10

    申请号:US11270903

    申请日:2005-11-10

    IPC分类号: G10L13/08

    CPC分类号: G10L13/06 G10L19/00

    摘要: A text to speech system (100) uses differential voice coding (230, 416) to compress a database of digitized speech waveform segments (210). A seed waveform (535) is used to precondition each speech waveform prior to encoding which, upon encoding, provides a seeded preconditioned encoded speech token (550). The seed portion (541) may be removed and the preconditioned encoded speech token portion (542) may be stored in a database for text to speech synthesis. When speech it to be synthesized, upon requesting the appropriate speech waveform for the present sound to be produced, the seed portion is preappended to the preconditioned encoded speech token for differential decoding.

    摘要翻译: 文本到语音系统(100)使用差分语音编码(230,416)来压缩数字化语音波形段(210)的数据库。 种子波形(535)用于在编码之前对每个语音波形进行预处理,在编码时,提供种子预条件编码语音令牌(550)。 种子部分(541)可以被去除,并且预条件编码语音令牌部分(542)可以被存储在用于文本到语音合成的数据库中。 当要合成语音时,在请求产生当前声音的适当语音波形时,将种子部分预先附加到预处理的编码语音令牌以进行差分解码。

    Hands-free push-to-talk radio
    2.
    发明申请
    Hands-free push-to-talk radio 审中-公开
    免提一键通电台

    公开(公告)号:US20060136201A1

    公开(公告)日:2006-06-22

    申请号:US11020423

    申请日:2004-12-22

    IPC分类号: G10L11/06

    CPC分类号: H04M1/6041 G10L25/78

    摘要: A hands-free digital push-to-talk device (102) includes a digital background noise suppressor (302), a digital voice activity detector (304), an audio buffer (306), as well as a decision handler (308), embedded inside the device's (102) digital signal processor (222). Audio is buffered until the decision handler (308) determines that speech is present on an audio stream fed to the voice activity detector (304). The decision handler (308) makes the decision by assigning weighted values to each voice activity detector (304) determination, the weighted value varying depending on the state of the device (102) and temporal distance from the present time.

    摘要翻译: 免提数字一键通设备(102)包括数字背景噪声抑制器(302),数字语音活动检测器(304),音频缓冲器(306)以及决策处理器(308) 嵌入设备(102)数字信号处理器(222)内部。 音频被缓冲,直到判定处理器(308)确定在馈送到语音活动检测器(304)的音频流上存在语音。 决策处理器(308)通过将加权值分配给每个语音活动检测器(304)来确定,该加权值根据设备(102)的状态和从当前时间的时间距离而变化。