HMM compensation based on non-uniform spectral compression for noisy speech recognition

Abstract

A robust speech feature extraction method based on the power law of hearing and non-uniform spectral compression technique is proposed, and the correspondent model compensation algorithm is given. The mismatch functions, reflecting the infections of additive noise and spectral compression, and the model compensation formulae are deduced. The experiment results show that the significant improvement is obtained over the popular VTS (Vector Taylor Series) by adopting those approaches. It's concluded that the proposed method can deal with the speech recognition tasks in different additive noisy environments. © 2008 IEEE.