Elements of information theory
Elements of information theory
Artificial Neural Networks: A Tutorial
Computer - Special issue: neural computing: companion issue to Spring 1996 IEEE Computational Science & Engineering
IEEE Transactions on Pattern Analysis and Machine Intelligence
Statistical Pattern Recognition: A Review
IEEE Transactions on Pattern Analysis and Machine Intelligence
AHUMADA: A large speech corpus in Spanish for speaker characterization and identification
Speech Communication - Speaker recognition and its commercial and forensic applications
Neural Networks: A Comprehensive Foundation
Neural Networks: A Comprehensive Foundation
Neural Networks for Pattern Recognition
Neural Networks for Pattern Recognition
Speaker identification in mismatch training and testing conditions
ICASSP '00 Proceedings of the Acoustics, Speech, and Signal Processing, 2000. on IEEE International Conference - Volume 02
Source separation in post-nonlinear mixtures
IEEE Transactions on Signal Processing
Quasi-nonparametric blind inversion of Wiener systems
IEEE Transactions on Signal Processing
Maximum likelihood linear programming data fusion for speaker recognition
Speech Communication
A simple approximation for fast nonlinear deconvolution
NOLISP'11 Proceedings of the 5th international conference on Advances in nonlinear speech processing
Hi-index | 0.01 |
In this paper we propose the inversion of nonlinear distortions in order to improve the recognition rates of a speaker recognizer system. We study the effect of saturations on the test signals, trying to take into account real situations where the training material has been recorded in a controlled situation, but the testing signals present some mismatch with the input signal level (saturations). The experimental results for speaker recognition shows that a combination of several strategies can improve the recognition rates with saturated test sentences from 80% to 89.39%, while the results with clean speech (without saturation) is 87.76% for one microphone, and for speaker identification can reduce the minimum detection cost function with saturated test sentences from 6.42% to 4.15%, while the results with clean speech (without saturation) is 5.74% for one microphone and 7.02% for the other one.