发明授权
US5878389A Method and system for generating an estimated clean speech signal from a
noisy speech signal
失效
用于从噪声语音信号产生估计干净语音信号的方法和系统
- 专利标题： Method and system for generating an estimated clean speech signal from a noisy speech signal
- 专利标题（中）： 用于从噪声语音信号产生估计干净语音信号的方法和系统
-
申请号： US496068申请日： 1995-06-28
-
公开(公告)号： US5878389A公开(公告)日： 1999-03-02
- 发明人: Hynek Hermansky , Eric A. Wan , Carlos M. Avendano
- 申请人： Hynek Hermansky , Eric A. Wan , Carlos M. Avendano
- 申请人地址： OR Beaverton
- 专利权人： Oregon Graduate Institute of Science & Technology
- 当前专利权人： Oregon Graduate Institute of Science & Technology
- 当前专利权人地址： OR Beaverton
- 主分类号： G10L21/02
- IPC分类号： G10L21/02 ; G10L3/02
摘要：
A method and system for generating an estimate of a clean speech signal extracts time trajections of short-term parameters from a noisy speech signal to obtain a plurality of frequency components each having a magnitude spectrum and a phase spectrum. The magnitude spectrum is then compressed, filtered and then decompressed to obtain a modified magnitude spectrum. The speech signal is then reconstructed using the original phase spectrum and the modified magnitude spectrum.
公开/授权文献
- US4955053A Solid state ringing switch 公开/授权日：1990-09-04
信息查询
