Multi-codebook vector quantization algorithm for speaker identification.

作者: Mohammed El-Henawy , Nemat S. Abdel Kader , Mohammed Abu El-Yazeed

DOI:

关键词: Speech recognitionPattern recognitionComputer scienceLinde–Buzo–Gray algorithmAlgorithmVector quantizationArtificial intelligenceDistortionCodebookMatching (graph theory)SpeedupIdentification (information)Learning vector quantization

摘要: 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 text-independent and reduce the number of distortion calculations during matching between test frame speakers’ codebooks. Experimental work has shown that proposed model speed up process without approximately decreasing accuracy.

参考文章(7)
M.F.A. El-Yazeed, N.S. Abdel Kader, M.M. El-Henawy, A modified group vector quantization algorithm for speaker identification midwest symposium on circuits and systems. ,vol. 2, pp. 629- 632 ,(2003) , 10.1109/MWSCAS.2003.1562365
Chang-Da Bei, R. Gray, An Improvement of the Minimum Distortion Encoding Algorithm for Vector Quantization IEEE Transactions on Communications. ,vol. 33, pp. 1132- 1133 ,(1985) , 10.1109/TCOM.1985.1096214
J.P. Campbell, Speaker recognition: a tutorial Proceedings of the IEEE. ,vol. 85, pp. 1437- 1462 ,(1997) , 10.1109/5.628714
Y. Linde, A. Buzo, R. Gray, An Algorithm for Vector Quantizer Design IEEE Transactions on Communications. ,vol. 28, pp. 84- 95 ,(1980) , 10.1109/TCOM.1980.1094577
Jialong He, Li Liu, G. Palm, A discriminative training algorithm for VQ-based speaker identification IEEE Transactions on Speech and Audio Processing. ,vol. 7, pp. 353- 356 ,(1999) , 10.1109/89.759047
Jeng-Shyang Pan, Zhe-Ming Lu, Sheng-He Sun, An efficient encoding algorithm for vector quantization based on subvector technique IEEE Transactions on Image Processing. ,vol. 12, pp. 265- 270 ,(2003) , 10.1109/TIP.2003.810587
R. Gray, Vector quantization IEEE Assp Magazine. pp. 75- 100 ,(1984)