NONPARAMETRIC DISTANCE MEASURES OF SPEAKER VERIFICATION

被引:2
作者
NG, KT [1 ]
LI, H [1 ]
HATON, JP [1 ]
SU, J [1 ]
机构
[1] CTR RECH INFORMAT NANCY,CNRS,BAT,LORIA,F-54506 VANDOEUVRE NANCY,FRANCE
关键词
SPEAKER RECOGNITION; SIGNAL PROCESSING;
D O I
10.1049/el:19950489
中图分类号
TM [电工技术]; TN [电子技术、通信技术];
学科分类号
0808 ; 0809 ;
摘要
A nonparametric technique for speaker recognition and verification is proposed. The proposed distance measures differ from existing distance measures by their symmetry. These measures have been evaluated on a text-dependent database, achieving a 99.6% verification rate for 200 French speakers. In addition, it is shown that the covariance carries more speaker information than the sample mean.
引用
收藏
页码:700 / 701
页数:2
相关论文
共 3 条
[1]  
BIMBOT F., MATHAN L., Second-order statistical measures for text-independent speaker identification, ESCA Workshop on Automatic Speaker Recognition, Identification and Verification, Martigny, pp. 51-54, (1994)
[2]  
GONG Y., HATON J.-P., Nonlinear vectorial interpolation for speaker recognition, ICASSP, (1992)
[3]  
DUDA R.O., HART P.E., Pattern classification and scene analysis, (1973)