DocumentCode :
3226939
Title :
Feature Comparison among Various Wavelets in Speaker Recognition Using Support Vector Machine
Author :
Lin, Chien-Chang ; Chen, Shi-Huang ; Lin, Tsung-Ching ; Truong, T.K.
Author_Institution :
Dept. of Inf. Eng., I-Shou Univ.
fYear :
2006
fDate :
Dec. 2006
Firstpage :
811
Lastpage :
816
Abstract :
In this paper, there are 17 types of wavelet coefficients obtained from the Matlab software and an Aurora-2 database used to evaluate which wavelet type has a better accuracy in speaker recognition. We first determine the frequency cepstral coefficient (FCC) level to form a 114-dimentional feature vector by the use of Daubechies-4 wavelet and support vector machines (SVMs) with pre-selected exponential radial basis kernel function (ERBF) and under some additional conditions. Then, average, for each wavelet, the accuracy of 42 possible combinations about the gender of speakers considered in seven kinds of experiments corresponding to two to eight speakers. The experimental results show that the best accuracy in average will be achieved by using the reverse biorthogonal-3.5 or reverse biorthogonal-3.7 wavelet. The reverse biorthogonal-3.5 wavelet is then chosen to be the proposed wavelet function for speaker recognition in terms of shorter filter length
Keywords :
cepstral analysis; mathematics computing; radial basis function networks; speaker recognition; support vector machines; wavelet transforms; 114-dimentional feature vector; Aurora-2 database; Daubechies-4 wavelet; FCC; Matlab software; SVM; exponential radial basis kernel function; frequency cepstral coefficient; preselected ERBF; reverse biorthogonal-3.5 wavelet; shorter filter length; speaker recognition; support vector machine; wavelet coefficients; Cepstral analysis; Data engineering; Fourier transforms; Mel frequency cepstral coefficient; Spatial databases; Speaker recognition; Speech; Support vector machine classification; Support vector machines; Wavelet transforms;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Multimedia, 2006. ISM'06. Eighth IEEE International Symposium on
Conference_Location :
San Diego, CA
Print_ISBN :
0-7695-2746-9
Type :
conf
DOI :
10.1109/ISM.2006.79
Filename :
4061264
Link To Document :
بازگشت