Improving the Performance of Speaker Verification Systems in Noisy Environments

Classical speech enhancement techniques and recently developed wavelet denoising schemes are applied to speaker verification systems in noise. Merely applying these techniques to corrupted testing signals does not properly decreases the error rates when clean speech is used for training signals. In this paper, a noise modelling approach is used to corrupt the training signals according to an estimate of the noise present in the test signal. We show that this procedure makes the error rates drop to a fraction of the original results.