9th Annual Conference of the International Speech Communication Association

Brisbane, Australia
September 22-26, 2008

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

Jun Du, Qiang Huo

Microsoft Research Asia, China

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.

Full Paper

Bibliographic reference.  Du, Jun / Huo, Qiang (2008): "A feature compensation approach using high-order vector taylor series approximation of an explicit distortion model for noisy speech recognition", In INTERSPEECH-2008, 1257-1260.