Combining MMSE enhancement with LA model adaptationforrobust automatic speech recognition
Pei Ding, Zhigang Cao · Electronics Letters · 2001
A new scheme for robust automatic speech recognition is presented. The scheme combines minimum mean square error (MMSE)-based enhancement with Log-Add (LA) model adaptation. Experimental evaluations show that the proposed MMSE-LA scheme can achieve significant improvement in recognition across a wide range of signal-to-noise ratios, especially in very noisy environments.