Exploring GMM-derived Features for Unsupervised Adaptation of Deep Neural Network Acoustic Models

摘要

In this paper we investigate GMM-derived features recently introduced for adaptation of context-dependent deep neural network HMM (CD-DNN-HMM) acoustic models. We present an initial attempt of improving the previously proposed adaptation algorithm by applying lattice scores and by using confidence measures in the traditional maximum a posteriori (MAP) adaptation algorithm. Modified MAP adaptation is performed for the auxiliary GMM model used in a speaker adaptation procedure for a DNN. In addition we introduce two approaches - data augmentation and data selection, for improving the regularization in MAP adaptation for DNN. Experimental results on the Wall Street Journal (WSJO) corpus show that the proposed adaptation technique can provide, on average, up to 9.9% relative word error rate (WER) reduction under an unsupervised adaptation setup, compared to speaker independent DNN-HMM systems built on conventional features.