发明名称 |
Method and means for a robust feature extraction for speech recognition |
摘要 |
<p>The present invention relates to a method and an apparatus for a robust feature extraction for speech recognition in a noisy environment, wherein the speech signal is segmented and is characterized by spectral components. The speech signal is splitted into a number of short term spectral components in L subbands, with L = 1,2,...and a noise spectrum from segments that only contain noise is estimated. Then a spectral subtraction of the estimated noise spectrum from the corresponding short term spectrum is performed and a probability for each short term spectrum component to contain noise is calculated. Finally these spectral component of each short-term spectrum, having a low probability to contain speech are interpolated in order to smooth those short-term spectra that only contain noise. With the interpolation the spectral components containing noise are interpolated by reliable spectral speech components that could be found in the neighborhood. <IMAGE></p> |
申请公布号 |
EP1096471(A1) |
申请公布日期 |
2001.05.02 |
申请号 |
EP19990203613 |
申请日期 |
1999.10.29 |
申请人 |
TELEFONAKTIEBOLAGET LM ERICSSON (PUBL) |
发明人 |
BRUECKNER, RAYMOND;HIRSCH, HANS-GUENTHER;KLISCH, RAINER;SPRINGER, VOLKER |
分类号 |
G10L15/02;G10L15/20;G10L21/0208;(IPC1-7):G10L15/20 |
主分类号 |
G10L15/02 |
代理机构 |
|
代理人 |
|
主权项 |
|
地址 |
|