This paper describes a new unsupervised, on-line and incremental speaker adaptation technique that improves the performance of speech recognition syst...

Dans cet article on propose une procédure robuste récursive pour l'identification d'un modèle non-stationnaire autorégressif (AR) du système de produc...

A robust speech recognizer is developed to tackle the inevitable mismatch between training and testing environments. Because the realistic environment...

We propose an adaptive short-term postfilter for speech coders by incorporating the properties of the pseudo-cepstrum [IEEE Trans. Speech Audio Proces...

Inter-speaker variability and sensitivity to background noise are two major problems in modern speech recognition systems. In this paper, we investiga...