论文信息 - A speaker identification system using a model of artificial neural networks for an elevator application

A speaker identification system using a model of artificial neural networks for an elevator application

Abstract This paper presents a comparison of some features for speaker identification applied to a building security system. The features used in this paper are pitch, frequency formants, linear predictive coding (LPC) coefficients and cepstral coefficients computed from LPC. The comparison was based on a system for building security that uses the voice of the residents to control the access to the building. The system uses a model of artificial neural network called multi-layer perceptron (MLP) as a classifier. This paper shows that cepstral coefficients are more efficient than LPC coefficients for the security system.

Dante Augusto Couto Barone | André Adami

[1] S. Furui,et al. Cepstral analysis technique for automatic speaker verification , 1981 .

[2] Ronald W. Schafer,et al. Digital Processing of Speech Signals , 1978 .

[3] Richard J. Mammone,et al. Speaker recognition using neural networks and conventional classifiers , 1994, IEEE Trans. Speech Audio Process..

[4] G.R. Doddington,et al. Speaker recognition—Identifying people by their voices , 1985, Proceedings of the IEEE.

[5] P. Gallinari,et al. A modular connectionist architecture for text-independent talker identification , 1991, IJCNN-91-Seattle International Joint Conference on Neural Networks.