This paper describes how the results of speaker verification systems can be improved and made robust with the use of a committee of neural networks for pattern recognition rather than the conventional single-network decision system. It illustrates the use of a supervised learning vector quantization neural network as the pattern classifier. Linear predictive coding and cepstral signal processing techniques are utilized to form hybrid feature parameter vectors to combat the effect of decreased recognition success with increased group size (number of speakers to be recognized)
V. Moonasar and G. K. Venayagamoorthy, "A Committee of Neural Networks for Automatic Speaker Recognition (ASR) Systems," Proceedings of the International Joint Conference on Neural Networks, 2001. IJCNN '01, Institute of Electrical and Electronics Engineers (IEEE), Jan 2001.
The definitive version is available at http://dx.doi.org/10.1109/IJCNN.2001.938844
International Joint Conference on Neural Networks, 2001. IJCNN '01
Electrical and Computer Engineering
Keywords and Phrases
Automatic Speaker Recognition; Cepstral Analysis; Cepstral Signal Processing; Learning (Artificial Intelligence); Linear Predictive Coding; Neural Nets; Neural Networks; Pattern Classification; Speaker Recognition; Speaker Verification; Supervised Learning; Vector Quantization
Article - Conference proceedings
© 2001 Institute of Electrical and Electronics Engineers (IEEE), All rights reserved.