DocumentCode :
2761596
Title :
Robust speech recognition using compression of Mel sub-band energies and temporal filtering
Author :
Moradi, Naghmeh ; Nasersharif, Babak ; Akbari, Ahmad
Author_Institution :
Fac. of Eng., Univ. of Guilan, Rasht, Iran
fYear :
2010
fDate :
4-6 Dec. 2010
Firstpage :
760
Lastpage :
764
Abstract :
The Mel-frequency cepstral coefficients (MFCC) are commonly used in speech recognition systems. But, they are highly sensitive to presence of external noise. In this paper, we propose a two-step method to compensate noise effects on MFCC. In the first step, we propose a sub-band SNR-dependent compression function for Mel sub-band energies to give higher weights to sub-bands less contaminated with noise and give lower weights to sub-bands more contaminated with noise. In the second step, we apply temporal filters to the weighted MFCCs in order to improve their temporal characteristics. Our results on Aurora2 databases show that the proposed method has higher performance than both of conventional temporal filtering methods and weighted MFCC.
Keywords :
cepstral analysis; filtering theory; speech recognition; Aurora2 databases; Mel sub-band energy; Mel-frequency cepstral coefficients; SNR-dependent compression; noise effects; speech recognition; temporal filtering; Filter banks; Mel frequency cepstral coefficient; Signal to noise ratio; Speech; Speech processing; Speech recognition; MFCC; Mel sub-band; SNR-dependent compression; temporal filtering;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Telecommunications (IST), 2010 5th International Symposium on
Conference_Location :
Tehran
Print_ISBN :
978-1-4244-8183-5
Type :
conf
DOI :
10.1109/ISTEL.2010.5734124
Filename :
5734124
Link To Document :
بازگشت