BINAURAL MASK-INFORMED SPEECH ENHANCEMENT FOR HEARING AIDS WITH HEAD TRACKING

An end-to-end speech enhancement system for hearing aids is proposed which seeks to improve the intelligibility of binaural speech in noise during head movement. The system uses a reference beamformer whose look direction is informed by knowledge of the head orientation and the a priori known direction of the desired source. From this a time-frequency mask is estimated using a deep neural network. The binaural signals are obtained using bilateral beamformers followed by a classical minimum mean square error speech enhancer, modified to use the estimated mask as a speech presence probability prior. In simulated experiments, the improvement in a binaural intelligibility metric (DBSTOI) given by the proposed system relative to beamforming alone corresponds to an SNR improvement of 4 to 6 dB. Results also demonstrate the individual contributions of incorporating the mask and the head orientation-aware beam steering to the proposed system.