Joint sparse representation based cepstral-domain dereverberation for distant-talking speech recognition

In this paper we address reducing the mismatch between training and testing conditions for robust distant-talking speech recognition under realistic reverberant environments. It is well known that the distortions caused by reverberation, background noise, etc., are highly nonlinear in the cepstral domain. In this paper we propose to capture the complex relationships between clean and reverberant speech via joint dictionary learning. Given a test reverberant speech with a sequence of feature vectors we first find their sparse representations, and then estimate the underlying clean feature vectors using the dictionary of clean speech. Based on speech recognition experiments conducted under realistic reverberation conditions, the proposed method is shown to perform very well, resulting in an average relative improvement of 59.1% compared with the baseline front-ends.