Integrating Source-Channel and Attention-Based Sequence-to-Sequence Models for Speech Recognition

@article{Li2019IntegratingSA,
  title={Integrating Source-Channel and Attention-Based Sequence-to-Sequence Models for Speech Recognition},
  author={Qiujia Li and Chao Zhang and Philip C. Woodland},
  journal={2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)},
  year={2019},
  pages={39-46}
}
  • Qiujia Li, Chao Zhang, Philip C. Woodland
  • Published 2019
  • Computer Science, Engineering
  • 2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)
  • This paper proposes a novel automatic speech recognition (ASR) framework called Integrated Source-Channel and Attention (ISCA) that combines the advantages of traditional systems based on the noisy source-channel model (SC) and end-to-end style systems using attention-based sequence-to-sequence models. The traditional SC system framework includes hidden Markov models and connectionist temporal classification (CTC) based acoustic models, language models (LMs), and a decoding procedure based on a… CONTINUE READING

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 70 REFERENCES

    End-to-end Speech Recognition With Word-Based Rnn Language Models

    VIEW 11 EXCERPTS
    HIGHLY INFLUENTIAL

    Component Fusion: Learning Replaceable Language Model Component for End-to-end Speech Recognition System

    • Changhao Shan, Chao Weng, +4 authors Lei Xie
    • Computer Science
    • ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
    • 2019

    Improving End-to-end Speech Recognition with Pronunciation-assisted Sub-word Modeling

    PyHTK: Python Library and ASR Pipelines for HTK

    VIEW 1 EXCERPT

    SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognition

    VIEW 3 EXCERPTS

    Windowed Attention Mechanisms for Speech Recognition

    A Comparison of Techniques for Language Model Integration in Encoder-Decoder Speech Recognition