Application of a generalized probabilistic descent method to recurrent neural network based speech recognition

Sin Horng Chen, Yuan Fu Liao, Wen Yuan Chen

Research output: Contribution to journalConference articlepeer-review

1 Scopus citations

Abstract

A new method is proposed in this paper to train recurrent neural networks (RNNs) for speech recognition such that the difficulty of selecting appropriate target functions can be avoided. A novel architecture of RNN-based speech recognition system is also introduced for solving the problem related to large vocabulary speech recognition. Additionally, the proposed RNN-based recognizer is found to have the advantages of being capable of absorbing the temporal variation of speech patterns as well as possessing effective discrimination capabilities. Performance of the proposed system was examined using two speech recognition tasks of recognizing 10 Mandarin digits and 54 confusable Mandarin syllables. Experimental results show that the proposed method outperforms both the continuous observation densities hidden Markov models method and a RNN recognizer using the extended back propagation training algorithm.

Original languageEnglish
Article number389571
Pages (from-to)II653-II656
JournalICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
Volume2
DOIs
StatePublished - 19 Apr 1994
EventProceedings of the 1994 IEEE International Conference on Acoustics, Speech and Signal Processing. Part 2 (of 6) - Adelaide, Aust
Duration: 19 Apr 199422 Apr 1994

Fingerprint Dive into the research topics of 'Application of a generalized probabilistic descent method to recurrent neural network based speech recognition'. Together they form a unique fingerprint.

Cite this