DocumentCode :
2395612
Title :
Weighted matching algorithms and reliability in noise cancelling by spectral subtraction
Author :
Yoma, Nestor Becerra ; McInnes, Fergus ; Jack, Mervyn
Author_Institution :
Centre for Commun. Interface Res., Edinburgh Univ., UK
Volume :
2
fYear :
1997
fDate :
21-24 Apr 1997
Firstpage :
1171
Abstract :
This paper addresses the problem of speech recognition with signals corrupted by additive noise at moderate SNR. A technique based on spectral subtraction and noise cancellation reliability weighting in acoustic pattern matching algorithms is studied. A model for additive noise is proposed and used to compute the variance of the hidden clean signal information and the reliability of the spectral subtraction process. The results presented show that a proper weight on the information provided by static parameters can substantially reduce the error rate
Keywords :
acoustic signal processing; noise; reliability; spectral analysis; speech processing; speech recognition; SNR; acoustic pattern matching algorithms; additive noise; error rate reduction; hidden clean signal information variance; noise cancellation reliability weighting; noise cancelling; spectral subtraction; speech recognition; static parameters; weighted matching algorithms; Additive noise; Error analysis; Filters; Hidden Markov models; Neural networks; Noise cancellation; Signal to noise ratio; Speech enhancement; Speech recognition; Testing;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Acoustics, Speech, and Signal Processing, 1997. ICASSP-97., 1997 IEEE International Conference on
Conference_Location :
Munich
ISSN :
1520-6149
Print_ISBN :
0-8186-7919-0
Type :
conf
DOI :
10.1109/ICASSP.1997.596151
Filename :
596151
Link To Document :
بازگشت