Rapid feature space MLLR speaker adaptation for deep neural network acoustic modeling

Abstract

Bilinear models based feature space Maximum Likelihood Linear Regression (FMLLR) speaker adaptation have showed good performance for GMM-HMMs especially when the amount of adaptation data is limited. In this paper, we propose using bilinear models feature as inputs to deep neural networks (DNNs) for rapid speaker adaptation of acoustic modeling to facilitate utterance-level normalization. The effectiveness of the proposed method is demonstrated with experiments on the Mandarin short message dictation and voice query dataset.