Feature Extraction Based on Wavelet Domain Hidden Markov Tree Model for Robust Speech Recognition

摘要

We present a new feature extraction method for robust speech recognition in the presence of additive white Gaussian noise. The proposed method is made up of two stages in cascade. The first stage is de-noising process based on the wavelet domain hidden Markov tree model, and the second one is reduction of the influence of the residual noise in the filter bank analysis. To evaluate the performance of the proposed method, recognition experiments were carried out for noisy speech with signal-to-noise ratio from 25 dB to 0 dB. Experiment results demonstrate the superiority of the proposed method to the conventional ones.