Donggan Speech Recognition Based on Convolution Neural Networks

Abstract

Donggan language, which is a special variant of Mandarin, is used by Donggan people in Central Asia. Donggan language includes Gansu dialect and Shaanxi dialect. This paper proposes a convolutional neural network (CNN) based Donggan language speech recognition method for the Donggan Shaanxi dialect. A text corpus and a pronunciation dictionary were designed for of Donggan Shannxi dialect and the corresponding speech corpus was recorded. Then the acoustic models of Donggan Shaanxi dialect was trained by CNN. Experimental results demonstrate that the recognition rate of proposed CNN-based method achieves lower word error rate than that of the monophonic hidden Markov model (HMM) based method, triphone HMM-based method and DNN- based method.