Who Needs Words? Lexicon-Free Speech Recognition

@article{Likhomanenko2019WhoNW,
  title={Who Needs Words? Lexicon-Free Speech Recognition},
  author={Tatiana Likhomanenko and Gabriel Synnaeve and Ronan Collobert},
  journal={CoRR},
  year={2019},
  volume={abs/1904.04479}
}
Lexicon-free speech recognition naturally deals with the problem of out-of-vocabulary (OOV) words. In this paper, we show that character-based language models (LM) can perform as well as word-based LMs for speech recognition, in word error rates (WER), even without restricting the decoding to a lexicon. We study character-based LMs and show that convolutional LMs can effectively leverage large (character) contexts, which is key for good speech recognition performance downstream. We specifically… CONTINUE READING
6
Twitter Mentions

Citations

Publications citing this paper.

References

Publications referenced by this paper.
SHOWING 1-10 OF 36 REFERENCES

End-to-end attention-based large vocabulary speech recognition

  • 2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
  • 2016
VIEW 8 EXCERPTS
HIGHLY INFLUENTIAL

Listen, attend and spell: A neural network for large vocabulary conversational speech recognition

  • 2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
  • 2016
VIEW 8 EXCERPTS
HIGHLY INFLUENTIAL

Character-based units for unlimited vocabulary continuous speech recognition

  • 2017 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)
  • 2017
VIEW 1 EXCERPT

Similar Papers

Loading similar papers…