Hybrid speech recognition with Deep Bidirectional LSTM

@article{Graves2013HybridSR,
  title={Hybrid speech recognition with Deep Bidirectional LSTM},
  author={Alex Graves and Navdeep Jaitly and Abdel-rahman Mohamed},
  journal={2013 IEEE Workshop on Automatic Speech Recognition and Understanding},
  year={2013},
  pages={273-278}
}
  • Alex Graves, Navdeep Jaitly, Abdel-rahman Mohamed
  • Published 2013
  • Computer Science
  • 2013 IEEE Workshop on Automatic Speech Recognition and Understanding
  • Deep Bidirectional LSTM (DBLSTM) recurrent neural networks have recently been shown to give state-of-the-art performance on the TIMIT speech database. [...] Key Result We conclude that the hybrid approach with DBLSTM appears to be well suited for tasks where acoustic modelling predominates. Further investigation needs to be conducted to understand how to better leverage the improvements in frame-level accuracy towards better word error rates.Expand Abstract

    Figures, Tables, and Topics from this paper.

    Citations

    Publications citing this paper.
    SHOWING 1-10 OF 892 CITATIONS

    A comprehensive study of deep bidirectional LSTM RNNS for acoustic modeling in speech recognition

    VIEW 1 EXCERPT
    CITES METHODS

    EESEN: End-to-end speech recognition using deep RNN models and WFST-based decoding

    Deep LSTM for Large Vocabulary Continuous Speech Recognition

    VIEW 1 EXCERPT
    CITES BACKGROUND

    Deep bi-directional recurrent networks over spectral windows

    VIEW 1 EXCERPT
    CITES BACKGROUND

    Maxout neurons based deep bidirectional LSTM for acoustic modeling

    Exploiting LSTM structure in deep neural networks for speech recognition

    • Tianxing He, Jasha Droppo
    • Computer Science
    • 2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
    • 2016
    VIEW 1 EXCERPT
    CITES BACKGROUND

    Densenet Blstm for Acoustic Modeling in Robust ASR

    VIEW 1 EXCERPT
    CITES BACKGROUND

    FILTER CITATIONS BY YEAR

    2013
    2020

    CITATION STATISTICS

    • 97 Highly Influenced Citations

    • Averaged 184 Citations per year from 2018 through 2020

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 19 REFERENCES

    Speech recognition with deep recurrent neural networks

    VIEW 4 EXCERPTS

    Revisiting Recurrent Neural Networks for robust ASR

    Bidirectional recurrent neural networks

    VIEW 1 EXCERPT

    Acoustic Modeling Using Deep Belief Networks

    VIEW 15 EXCERPTS