DocumentCode :
2426446
Title :
An auditory model for robust speech recognition
Author :
Luo, Xuewen ; Soon, Ing Yann ; Yeo, Chai Kiat
Author_Institution :
Sch. of Electr. & Electron. Eng., Nanyang Technol. Univ., Singapore
fYear :
2008
fDate :
7-9 July 2008
Firstpage :
1105
Lastpage :
1109
Abstract :
Performance of automatic speech recognition system drops dramatically in the presence of background noise unlike the human auditory system which is more adept at noisy speech recognition. This paper proposes a novel auditory modelling algorithm which is integrated with a feature extraction front-end. The proposed algorithm simulates properties of the human auditory system and applies it to the speech recognition system to enhance its robustness. It integrates simultaneous masking, forward masking and temporal integration effects into traditional mel-frequency cepstral coefficients (MFCC) feature extraction algorithm for robust speech recognition. The proposed method sharpens the power spectrum of the signal in both the frequency domain and the time domain. Experiments carried out on AURORA2 database show that the word recognition rate using our proposed feature extraction method has been effectively increased.
Keywords :
feature extraction; hearing; speech recognition; AURORA2 database; auditory modelling algorithm; automatic speech recognition system; background noise; feature extraction; forward masking; human auditory system; mel-frequency cepstral coefficients; noisy speech recognition; robust speech recognition; temporal integration; word recognition; Auditory system; Automatic speech recognition; Background noise; Cepstral analysis; Feature extraction; Frequency domain analysis; Humans; Mel frequency cepstral coefficient; Noise robustness; Speech recognition;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Audio, Language and Image Processing, 2008. ICALIP 2008. International Conference on
Conference_Location :
Shanghai
Print_ISBN :
978-1-4244-1723-0
Electronic_ISBN :
978-1-4244-1724-7
Type :
conf
DOI :
10.1109/ICALIP.2008.4590203
Filename :
4590203
Link To Document :
بازگشت