Sixth International Conference on Spoken Language Processing
(ICSLP 2000)

Beijing, China
October 16-20, 2000

Two-Stage Speaker Identification System Based On VQ and NBDGMM

Luo Si, Qi Xiu Hu

Department of Computer Science, Tsinghua University, Beijing, China

In this paper, a new speaker identification system is presented. The system can be divided into two subsystems, one close-set speaker identification system and one speaker verification system. The VQ model is used in the close-set speaker identification system and a new method called NBDGMM (Normalization Based on Difference of GMM) is introduced. Experiments have been done to prove that this speaker identification system is efficient.


Full Paper

Bibliographic reference.  Si, Luo / Hu, Qi Xiu (2000): "Two-stage speaker identification system based on VQ and NBDGMM", In ICSLP-2000, vol.2, 282-285.