A model distance maximizing framework for speech recognizer-based speech enhancement

This paper has presented a novel discriminative parameter calibration approach based on the model distance maximizing (MDM) framework to improve the performance of our previously-proposed method based on spectral subtraction (SS) in a likelihood-maximizing framework. In the previous work, spectral over-subtraction factors were adjusted based on the conventional maximum-likelihood (ML) approach that utilized only the true model and did not consider other confused models, thus likely reached suboptimal solutions. While in the proposed MDM framework, improved speech recognition performance is obtained by maximizing the dissimilarities among models. Experimental results based on FARSDAT, TIMIT and real distant-talking databases have demonstrated that the MDM framework outperformed ML in terms of recognition accuracy.