发明名称 |
Method and device for discriminating voiced and unvoiced sounds |
摘要 |
A method and a device for discriminating a voiced sound from an unvoiced sound or background noise in speech signals are disclosed. Each block or frame of input speech signals is divided into plural sub-blocks and the standard deviation, effective value or the peak value is detected in a detection unit for detecting statistical characteristics from one sub-block to another. A bias detection unit detects a bias on the time scale of the standard deviation, effective value or the peak value to decide whether the speech signals are voiced or unvoiced from one block to another.
|
申请公布号 |
US5664052(A) |
申请公布日期 |
1997.09.02 |
申请号 |
US19930048034 |
申请日期 |
1993.04.14 |
申请人 |
SONY CORPORATION |
发明人 |
NISHIGUCHI, MASAYUKI;MATSUMOTO, JUN |
分类号 |
G10L11/02;G06F17/18;G10L11/06;G10L15/02;G10L15/04;(IPC1-7):G10L9/00 |
主分类号 |
G10L11/02 |
代理机构 |
|
代理人 |
|
主权项 |
|
地址 |
|