Example-based speech enhancement with joint utilization of spatial, spectral temporal cues of speech and noise

摘要

This paper proposes a multichannel speech enhancement technique that leverages three essential cues embedded in the observed signal, i.e., spatial, spectral and temporal cues, for differentiating target clean speech components from noise. The proposed method estimates clean-speech and noise features using a single optimization criterion by integrating two approaches, namely, example- and model-based multichannel speech enhancement approaches: The former utilizes spectral and temporal cues, while the latter exploits the spatial and spectral cues. We experimentally show the superiority of the proposed method over the conventional methods in terms of the automatic keyword recognition performance in adverse and highly nonstationary noisy environment.