Authors: Mangesh S. Deshpande, Raghunath S. Holambe
Addresses: Department of Electronics and Telecommunication Engineering, SRES's College of Engineering, Kopargaon, Maharashtra, India. ' Department of Instrumentation Engineering, SGGS Institute of Engineering and Technology, Nanded, Maharashtra, India
Abstract: A robust feature set, Teager Energy Operator based Cepstral Coefficients (TEOCC) for speaker identification task is proposed in this paper. Admissible Wavelet Packet (AWP) transform and the Teager Energy Operator (TEO) is used to obtain robust features. The proposed features significantly improve the speaker identification performance (76.25%) compared with the Mel Frequency Cepstral Coefficient (MFCC) features (57%) in the presence of car noise. The performance is evaluated using TIMIT and NOISEX-92 databases. This paper shows that higher-frequency bands also carry more speaker-specific information and the identification rate can be improved without additional processing of the signal to remove noise.
Keywords: speaker identification; wavelet transform; TEO; Teager energy operator; MFCC; mel frequency cepstral coefficient; car noise; vehicle noise; robust features; biometrics; speaker recognition; feature selection; AWP transform; frequency bands.
International Journal of Biometrics, 2011 Vol.3 No.3, pp.189 - 205
Published online: 24 Jan 2015 *Full-text access for editors Access for subscribers Purchase this article Comment on this article