DocumentCode :
3433827
Title :
A recursive feature vector normalization approach for robust speech recognition in noise
Author :
Viikki, Olli ; Bye, David ; Laurila, Kari
Author_Institution :
Nokia Res. Center, Tampere, Finland
Volume :
2
fYear :
1998
fDate :
12-15 May 1998
Firstpage :
733
Abstract :
The acoustic mismatch between testing and training conditions is known to severely degrade the performance of speech recognition systems. Segmental feature vector normalization was found to improve the noise robustness of mel-frequency cepstral coefficients (MFCC) feature vectors and to outperform other state-of-the-art noise compensation techniques in speaker-dependent recognition. The objective of feature vector normalization is to provide environment-independent parameter statistics in all noise conditions. We propose a more efficient implementation approach for feature vector normalization where the normalization coefficients are computed in a recursive way. Speaker-dependent recognition experiments show that the recursive normalization approach obtains over 60%, the segmental method approximately 50%, and parallel model combination a 14% overall error rate reduction, respectively. Moreover, in the recursive case, this performance gain is obtained with the smallest implementation costs. Also in speaker-independent connected digit recognition, over a 16% error rate reduction is obtained with the proposed feature vector normalization approach
Keywords :
cepstral analysis; error statistics; feature extraction; noise; recursive estimation; speech processing; speech recognition; MFCC feature vectors; acoustic mismatch; environment-independent parameter statistics; error rate reduction; experiments; hands-free voice dialling systems; implementation costs; mel-frequency cepstral coefficients; noise compensation; noise robustness; normalization coefficients; parallel model combination; performance; recursive feature vector normalization; recursive normalization; robust speech recognition; segmental feature vector normalization; speaker-dependent recognition; speaker-independent connected digit recognition; testing conditions; training conditions; Acoustic noise; Acoustic testing; Cepstral analysis; Degradation; Error analysis; Mel frequency cepstral coefficient; Noise robustness; Speech recognition; System testing; Working environment noise;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Acoustics, Speech and Signal Processing, 1998. Proceedings of the 1998 IEEE International Conference on
Conference_Location :
Seattle, WA
ISSN :
1520-6149
Print_ISBN :
0-7803-4428-6
Type :
conf
DOI :
10.1109/ICASSP.1998.675369
Filename :
675369
Link To Document :
بازگشت