THE USE OF RECURRENT NEURAL NETWORKS IN CONTINUOUS SPEECH RECOGNITION

@inproceedings{Robinson1996THEUO,
  title={THE USE OF RECURRENT NEURAL NETWORKS IN CONTINUOUS SPEECH RECOGNITION},
  author={T. Robinson and M. Hochberg and S. Renals},
  year={1996}
}
  • T. Robinson, M. Hochberg, S. Renals
  • Published 1996
  • Computer Science
  • This chapter describes a use of recurrent neural networks (i.e., feedback is incorporated in the computation) as an acoustic model for continuous speech recognition. [...] Key Method For each frame of acoustic data, the recurrent network generates an estimate of the posterior probability of of the possible phones given the observed acoustic signal.Expand Abstract
    Bidirectional recurrent neural networks
    • 3,292
    • Open Access
    RECURRENT NEURAL NETWORKS FOR ACOUSTIC MODELLING
    Boosting the performance of connectionist large vocabulary speech recognition
    • 39
    • Open Access
    High Order Recurrent Neural Networks for Acoustic Modelling
    • 8
    • Open Access
    Data selection and model combination in connectionist speech recognition
    • 3

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 34 REFERENCES