A Binaural Auditory Model for Missing Data Recognition of Speech in Noise

We describe a binaural auditory model for speech recognition, which is robust in the presence of reverberation and spatially separated noise intrusions. The principle underlying the model is to identify time-frequency regions which constitute reliable evidence of the speech signal. This is achieved both by determining the spatial location of the speech source, and by applying a simple model of reflection masking. Reliable timefrequency regions are passed to a missing data speech recognizer. We show, firstly, that the auditory model improves recognition performance in various reverberation conditions when no noise intrusion is present. Secondly, we demonstrate that the model improves performance when the speech signal is contaminated by noise, both for an anechoic environment and in the presence of simulated room reverberation.