Research on Mongolian Speech Recognition Based on FSMN

Abstract

Deep Neural Network (DNN) model has been achieved a significant result over the Mongolian speech recognition task, however, compared to Chinese, English or the others, there are still opportunities for further enhancements. This paper presents the first application of Feed-forward Sequential Memory Network (FSMN) for Mongolian speech recognition tasks to model long-term dependency in time series without using recurrent feedback. Furthermore, by modeling the speaker in the feature space, we extract the i-vector features and combine them with the Fbank features as the input to validate their effectiveness in Mongolian ASR tasks. Finally, discriminative training was firstly conducted over the FSMN by using maximum mutual information (MMI) and state-level minimum Bayes risk (sMBR), respectively. The experimental results show that: FSMN possesses better performance than DNN in the Mongolian ASR, and by using i-vector features combined with Fbank features as FSMN input and discriminative training, the word error rate (WER) is relatively reduced by 17.9% compared with the DNN baseline.