Intelligibility improvements using binaural diverse sub-band processing applied to speech corrupted with automobile noise

The paper reports on experiments assessing the capability of a diverse proc essing, multi-microphone sub-band adaptive signal processing scheme for imp roving the intelligibility of speech corrupted with automobile noise. Resul ts from formal listening tests demonstrate a significant improvement in the intelligibility and quality of the processed speech. Spoken digits corrupt ed with automobile noise at a low and a high signal-to-noise ratio were use d with two commercial speech recognisers. The results obtained with the rec ognisers did not demonstrate any statistically significant improvement due to processing in sub-bands.