An Improved Tibetan Lhasa Speech Recognition Method Based on Deep Neural Network

摘要

Deep Neural Networks (DNN) are the dominant technique widely used in English and Chinese speech recognition currently. However, Tibetan speech recognition research starts late and mainly uses Hidden Markov Model (HMM). In this paper, We show a better method of replacing Gaussian Mixture Models (GMM) by DNN to Tibetan Lhasa dialect speech recognition system. The system contains seven layers of features and a very large number of parameters. The Tibetan Lhasa dialect speech recognition system is implemented by combining the ability of sequence modeling with HMM. DNN has recently proved to be very effective for a variety of machine learning problems. From the results, we can find that the word error rate(WER) of Tibetan speech recognition is reduced from 41.7% to 28.3% compared with the basic HMM.