An application of recurrent nets to phone probability estimation

  title={An application of recurrent nets to phone probability estimation},
  author={Anthony J. Robinson},
  journal={IEEE transactions on neural networks},
  volume={5 2},
This paper presents an application of recurrent networks for phone probability estimation in large vocabulary speech recognition. The need for efficient exploitation of context information is discussed; a role for which the recurrent net appears suitable. An overview of early developments of recurrent nets for phone recognition is given along with the more recent improvements that include their integration with Markov models. Recognition results are presented for the DARPA TIMIT and Resource… CONTINUE READING

From This Paper

Topics from this paper.


Publications referenced by this paper.
Showing 1-10 of 13 references

CDNN: A context dependent neural network for continuous speech recognition,

  • N. Morgan, C. Wooters, S. Renals
  • in Proc. ICASSP,
  • 1992

Learning internal representations by error propagation , ” in

  • R. J. Williams
  • Parallel Distributed Processing : Explorations in…
  • 1992

Several improvements to a recurrent error propagation network phone recognition system,’

  • T. Robinson
  • Tech. Rep. CUEDFINFENGRR.82
  • 1991

Soft weight-sharing,” in Advances in Neural Itformation Pmcessin,y Systems

  • S. J. Nowlan, G. E. Hinton
  • 1991

A probabilistic approach to the understanding and training of neural network classifiers,

  • H. Gish
  • IEEE Transactions on Pattern Analysis and Machine…
  • 1990

An Alphanet approach to optimising input transformations for continuous speech recognition , ” in Proc . ICASSP ,

  • L. T. Niles, H. F. Silverman
  • 1990

Similar Papers

Loading similar papers…