Hard-limited Karhunen-Loeve transform for text independent speaker recognition

被引:10
作者
Chen, CCT [1 ]
Chen, CT [1 ]
Tsai, CM [1 ]
机构
[1] Natl Sun Yat Sen Univ, Dept Elect Engn, Kaohsiung 800, Taiwan
关键词
speaker recognition; speech recognition; spectral analysis;
D O I
10.1049/el:19971429
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 text independent speaker recognition system based on hard-limited eignfunctions derived from the Karhunen-Loeve transform is proposed. Two databases, each with 100 Mandarin speakers, are collected for system evaluation. It is demonstrated that > 94% correct classification rates can be achieved by the use of the first 32 hard-limited features.
引用
收藏
页码:2014 / 2016
页数:3
相关论文
共 2 条
[1]   A SPECTRAL FEATURE DESIGN SYSTEM FOR THE HIRIS-MODIS ERA [J].
CHEN, CCT ;
LANDGREBE, DA .
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 1989, 27 (06) :681-686
[2]   LONG-TERM FEATURE AVERAGING FOR SPEAKER RECOGNITION [J].
MARKEL, JD ;
OSHIKA, BT ;
GRAY, AH .
IEEE TRANSACTIONS ON ACOUSTICS SPEECH AND SIGNAL PROCESSING, 1977, 25 (04) :330-337