A robust environment-effects suppression training algorithm for adverse Mandarin speech recognition

In this paper, a new robust training algorithm for the generation of a set of bias-removed, noise-suppressed reference speech HMM models directly from a training database collected in adverse environment suffering with both convolutional channel bias and additive noise is proposed. Its main idea is to incorporate a signal biascompensation operation and a PMC noise-compensation operation into its iterative training process in order to make the resulting speech HMM models more suitable to the given robust speech recognition method using the same signal bias-compensation and PMC noisecompensation operations in the recognition process. Experimental results showed that the speech HMM models it generated outperformed both the clean-speech HMM models and those generated by the conventional k-means algorithm for two adverse Mandarin speech recognition tasks. So it is a promising robust training algorithm.