A Feature Compensation Approach Using High-Order Vector Taylor Series Approximation of an Explicit Distortion Model for Noisy Speech Recognition

This paper presents a new feature compensation approach to noisy speech recognition by using high-order vector Taylor series (HOVTS) approximation of an explicit model of environmental distortions. Formulations for maximum likelihood (ML) estimation of noise model parameters and minimum mean-squared error (MMSE) estimation of clean speech are derived. Experimental results on Aurora2 database demonstrate that the proposed approach achieves consistently significant improvement in recognition accuracy compared to traditional first-order VTS based feature compensation approach.