ROBUST SPEECH RECOGNITION IN ADDITIVE AND CONVOLUTIONAL NOISE USING PARALLEL MODEL COMBINATION

The method of Parallel Model Combination (PMC) has been shown to be a powerful technique for compensating a speech recognizer for the effects of additive noise. In this paper, the PMC scheme is extended to include the effects of convolutional noise. This is done by introducing a modified ''mismatch'' function which allows an estimate to be made of the difference in channel conditions or tilt between training and test environments. Having estimated this tilt, Maximum Likelihood (ML) estimates of the corrupted speech model may then be obtained in the usual way. The scheme is evaluated using the NOISEX-92 database where the performance in the presence of both interfering additive noise and convolutional noise shows only slight degradation compared with that obtained when no convolutional noise is present. (C) 1995 Academic Press