Context-dependent deep neural networks for commercial Mandarin speech recognition applications

Recently, context-dependent deep neural network hidden Markov models (CD-DNN-HMMs) have been successfully used in some commercial large-vocabulary English speech recognition systems. It has been proved that CD-DNN-HMMs significantly outperform the conventional context-dependent Gaussian mixture model (GMM)-HMMs (CD-GMM-HMMs). In this paper, we report our latest progress on CD-DNN-HMMs for commercial Mandarin speech recognition applications in Baidu. Experiments demonstrate that CD-DNN-HMMs can get relative 26% word error reduction and relative 16% sentence error reduction in Baidu´s short message (SMS) voice input and voice search applications, respectively, compared with state-of-the-art CD-GMM-HMMs trained using fMPE. To the best of our knowledge, this is the first time the performances of CD-DNN-HMMs are reported for commercial Mandarin speech recognition applications. We also propose a GPU on-chip speed-up training approach which can achieve a speed-up ratio of nearly two for DNN training.