Stochastic recurrent neural network for speech recognition

Jen-Tzung Chien, Chen Shen

    研究成果: Conference article同行評審

    6 引文 斯高帕斯(Scopus)

    摘要

    This paper presents a new stochastic learning approach to construct a latent variable model for recurrent neural network (RNN) based speech recognition. A hybrid generative and discriminative stochastic network is implemented to build a deep classification model. In the implementation, we conduct stochastic modeling for hidden states of recurrent neural network based on the variational auto-encoder. The randomness of hidden neurons is represented by the Gaussian distribution with mean and variance parameters driven by neural weights and learned from variational inference. Importantly, the class labels of input speech frames are incorporated to regularize this deep model to sample the informative and discriminative features for reconstruction of classification outputs. We accordingly propose the stochastic RNN (SRNN) to reflect the probabilistic property in RNN classification system. A stochastic error backpropagation algorithm is implemented. The experiments on speech recognition using TIMIT and Aurora4 show the merit of the proposed SRNN.

    原文English
    頁(從 - 到)1313-1317
    頁數5
    期刊Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH
    2017-August
    DOIs
    出版狀態Published - 1 一月 2017
    事件18th Annual Conference of the International Speech Communication Association, INTERSPEECH 2017 - Stockholm, Sweden
    持續時間: 20 八月 201724 八月 2017

    指紋

    深入研究「Stochastic recurrent neural network for speech recognition」主題。共同形成了獨特的指紋。

    引用此