DocumentCode :
1908684
Title :
Robust speaker identification using vocal source information
Author :
Nidhyananthan, S. Selva ; Kumari, R. Shantha Selva ; Jaffino, G.
Author_Institution :
Mepco Schlenk Eng. Coll., Sivakasi, India
fYear :
2012
fDate :
15-16 March 2012
Firstpage :
182
Lastpage :
186
Abstract :
This paper highlights the effectiveness of Wavelet Octave COefficients of Residues (WOCOR) based feature extraction for robust text-independent speaker identification. A new feature set, WOCOR is proposed to capture the spectro temporal source excitation characteristics of the speech signal. This work is focused to increase the identification accuracy with databases containing short length speech signal. Experimental evaluation is carried out on TIMIT database with 630 speakers using Gaussian Mixture Model (GMM) is used as classifier. Vocal source feature is used to extract the information from the residual signal. The vocal source information contains pitch, pitch frequency and phase in the residual signal. In this project, 93.02% Identification rate is achieved in WOCOR.
Keywords :
Gaussian processes; acoustic signal processing; feature extraction; signal classification; spatiotemporal phenomena; speaker recognition; speech processing; text analysis; wavelet transforms; Gaussian mixture model; TIMIT database; WOCOR; feature extraction; residual signal; robust text independent speaker identification; signal classifier; spectro temporal source excitation; speech signal processing; vocal source information extraction; wavelet octave coefficient of residue; Computational modeling; Context; Educational institutions; Robustness; Gaussian Mixture Model; Residual signal; Speaker identification; Vocal source Feature;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Devices, Circuits and Systems (ICDCS), 2012 International Conference on
Conference_Location :
Coimbatore
Print_ISBN :
978-1-4577-1545-7
Type :
conf
DOI :
10.1109/ICDCSyst.2012.6188700
Filename :
6188700
Link To Document :
بازگشت