论文信息 - Text-Independent Speaker Verification: The WCL-1 System

Text-Independent Speaker Verification: The WCL-1 System

A text-independent Probabilistic Neural Network (PNN)-based speaker verification system, referred to as WCL-1, is presented. A modular structure, with a distinct PNN for each enrolled speaker, is employed. A gender-dependent universal background model is created to represent the world of possible impostor speakers. Beside portrayal of the WCL-1 system, a compre-hensive description of the results obtained in the one-speaker detection task, during the 2002 NIST Speaker Recognition Evaluation is presented.

[1] Aaron E. Rosenberg,et al. A comparative performance study of several pitch detection algorithms , 1976 .

[2] J. A. Hartigan,et al. A k-means clustering algorithm , 1979 .

[3] M. J. Cheng,et al. Comparative performance study of several pitch detection algorithms , 1975 .

[4] Donald F. Specht,et al. Probabilistic neural networks , 1990, Neural Networks.