Title :
Robust automatic speech recognition in the presence of impulsive noise
Author :
Potamitis, I. ; Fakotakis, N. ; Kokkinakis, G.
Author_Institution :
Lab. of Wire Commun., Patras Univ., Greece
fDate :
6/7/2001 12:00:00 AM
Abstract :
A technique for suppressing the effect of any type of impulsive noise in the context of automatic speech recognition (ASR) is presented. The authors suggest the interposition in the mel frequency cepstral coefficients (MFCC) feature extraction front-end of (i) an identification stage responsible for the detection of corrupted cepstral vectors and (ii) a restoration stage that acts locally on the degraded cepstrum
Keywords :
cepstral analysis; feature extraction; identification; impulse noise; interference suppression; speech recognition; corrupted cepstral vectors detection; degraded cepstrum; feature extraction front-end; identification stage; impulsive noise suppression; mel frequency cepstral coefficients; restoration stage; robust automatic speech recognition;
Journal_Title :
Electronics Letters
DOI :
10.1049/el:20010501
