INTEGRATING DNN-BASED AND SPATIAL CLUSTERING-BASED MASK ESTIMATION FOR ROBUST MVDR BEAMFORMING

Recently, time-frequency mask-based beamforming has been extensively studied as the frontend of deep neural network (DNN) based automatic speech recognition (ASR) in noisy environments. Two mask estimation approaches have been separately developed for this beamforming method, namely the the DNN-based approach, which exploits the time-frequency features of the signal, and the spatial c1ustering-based approach, which exploits the spatial features ofthe signal. This paper proposes a new method that integrates the two approaches in a probabilistic way to further improve mask estimati on by exploiting the advantages of both approaches. Experiments using the real data ofthe CHiME-3 multichannel noisy speech corpus show that the proposed method almost always outperforms the conventional approaches in terms ofword error rate (WER) improvement.