DocumentCode :
454535
Title :
Kurtosis Normalization in Feature Space for Robust Speaker Verification
Author :
Xie, Yanlu ; Dai, Beiqian ; Yao, Zhiqiang ; Liu, Minghui
Author_Institution :
Microsoft Key Lab. of Multimedia Comput. & Commun., Univ. of Sci. & Technol. of China, Hefei
Volume :
1
fYear :
2006
fDate :
14-19 May 2006
Abstract :
The acoustic mismatch between the training and test environments will lead to the difference of the statistical characteristics of speech parameters. Since the statistical characteristics of the kurtosis can measure the non-Gaussianity of a random variable, kurtosis normalization will make the training and test speech parameters match the standard normal distribution in some sense. In this paper, a kurtosis normalization method using sigmoid functions (logit functions) in feature space is presented for GMM-UBM based text-independent speaker verification system. Experimental results on the 2004 NIST SRE database show that with the new method significant improvement can be achieved in not only equal error rate but also minimum detection cost compared with baseline system (more than 33% relative reduction for long speech)
Keywords :
speaker recognition; statistical analysis; acoustic mismatch; kurtosis normalization; logit functions; robust speaker verification; sigmoid functions; statistical characteristics; text-independent speaker verification system; Acoustic measurements; Acoustic testing; Gaussian distribution; Loudspeakers; Measurement standards; NIST; Random variables; Robustness; Spatial databases; Speech;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Acoustics, Speech and Signal Processing, 2006. ICASSP 2006 Proceedings. 2006 IEEE International Conference on
Conference_Location :
Toulouse
ISSN :
1520-6149
Print_ISBN :
1-4244-0469-X
Type :
conf
DOI :
10.1109/ICASSP.2006.1659971
Filename :
1659971
Link To Document :
بازگشت