8th International Conference on Spoken Language Processing

Jeju Island, Korea
October 4-8, 2004

Multi-Codebook Vector Quantization Algorithm for Speaker Identification

Mohammed Abu El-Yazeed (1), Nemat Abdel Kader (1), Mohammed El-Henawy (2)

(1) Cairo University
(2) Egypt National Telecommunication Institute, Egypt

This paper introduces an algorithm for speaker identification based on multi-codebook vector quantization (MCVQ). MCVQ combines different size codebooks to achieve high recognition accuracy for text-independent speaker identification and reduce the number of distortion calculations during matching between test frame and speakers' codebooks. Experimental work has shown that the proposed model speed up the matching process without approximately decreasing the identification accuracy.

Full Paper

Bibliographic reference.  El-Yazeed, Mohammed Abu / Kader, Nemat Abdel / El-Henawy, Mohammed (2004): "Multi-codebook vector quantization algorithm for speaker identification", In INTERSPEECH-2004, 1809-1812.