论文信息 - Research of speaker identification based on little training data

Research of speaker identification based on little training data

This paper summarizes several current methods and analyses of the existing problems in directing against little training data for speaker identification. A new algorithm based on support vector machine is presented in the paper, and is used to build a constrained text-independent speaker identification system. Experimental results indicate that the performance of the test system is better than the system based on VQ, HMM or NN as comparison.

Wei Chen | Ai-Guo Gao | Yao-Quan Yang | Yu-Dong Lu

[1] John C. Platt,et al. Fast training of support vector machines using sequential minimal optimization, advances in kernel methods , 1999 .

[2] Vladimir N. Vapnik,et al. The Nature of Statistical Learning Theory , 2000, Statistics for Engineering and Information Science.

[3] Colin Campbell,et al. Algorithmic approaches to training Support Vector Machines: a survey , 2000, ESANN.

[4] H. Gish,et al. Text-independent speaker identification , 1994, IEEE Signal Processing Magazine.

[5] Stephen A. Zahorian,et al. A partitioned neural network approach for vowel classification using smoothed time/frequency features , 1999, IEEE Trans. Speech Audio Process..