Noise adaptive speech recognition with acoustic models trained from noisy speech evaluated on Aurora-2 database

Abstract

In this paper, we apply the noise adaptive speech recognition for noisy speech recognition in non-stationary noise to the situation that acoustic models are trained from noisy speech. We justify it by that the noise adaptive speech recognition includes iterative processes between a noise parameter estimation step and a model adaptation step, which can possibly do non-linear mapping between the original training space and that for recognition. Experiments were performed on Aurora-2 task with multi-conditional training set which includes noisy utterances. Through experiments, we observed that the noise adaptive speech recognition can have better performance than the baseline system trained from multi-conditional training set without noise adaptive speech recognition.