Stochastic recurrent neural network for speech recognition

Jen-Tzung Chien, Chen Shen

Research output: Contribution to journalConference articlepeer-review

5 Scopus citations

Abstract

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.

Original languageEnglish
Pages (from-to)1313-1317
Number of pages5
JournalProceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH
Volume2017-August
DOIs
StatePublished - 1 Jan 2017
Event18th Annual Conference of the International Speech Communication Association, INTERSPEECH 2017 - Stockholm, Sweden
Duration: 20 Aug 201724 Aug 2017

Keywords

  • Neural network
  • Speech recognition
  • Stochastic error backpropagation
  • Variational inference

Fingerprint Dive into the research topics of 'Stochastic recurrent neural network for speech recognition'. Together they form a unique fingerprint.

Cite this