Spectral subtraction in likelihood-maximizing framework for robust speech recognition

Spectral Subtraction (SS), as a speech enhancement technique, originally designed for improving quality of speech signal judged by human listeners. it usually improve the quality and intelligibility of speech signals, while the speech recognition systems need compensation techniques capable of reducing the mismatch between the noisy speech features and the clean models. This paper proposes a novel approach for solving this problem by considering the SS and the speech recognizer as two interconnected components, sharing the common goal of improved speech recognition accuracy. The experimental evaluations on a real recorded database and the TIMIT database show that the proposed method can achieve significant improvement in recognition rate across a wide range of the signal to noise ratios.