Adaptive beamformer with recursively updated quadratic constraints

A novel adaptive beamformer employing recursively updated soft constraints for acoustic speech enhancement is proposed. The beamformer operates in a subband structure to allow time-frequency operation for each channel. As such, the processing can be viewed as a combination of weighted spatial and temporal filters. The major benefit of this recursive soft constrained beamformer is that it allows the possibility of using the spectral information of the desired source to modify the soft constraint. This has clear benefits on the speech distortion of the source of interest. The novel adaptive beamformer involves continuous modification of the soft constraint by feeding back the spectral content of the estimated output speech signal. Evaluations on real car data show that the proposed algorithm significantly improves the speech quality with noise suppression levels up to 17 dB.