Advances in all-neural speech recognition

@article{Zweig2017AdvancesIA,
  title={Advances in all-neural speech recognition},
  author={Geoffrey Zweig and Chengzhu Yu and Jasha Droppo and Andreas Stolcke},
  journal={2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)},
  year={2017},
  pages={4805-4809}
}
This paper advances the design of CTC-based all-neural (or end-to-end) speech recognizers. We propose a novel symbol inventory, and a novel iterated-CTC method in which a second system is used to transform a noisy initial output into a cleaner version. We present a number of stabilization and initialization methods we have found useful in training these networks. We evaluate our system on the commonly used NIST 2000 conversational telephony test set, and significantly exceed the previously… CONTINUE READING
Highly Cited
This paper has 56 citations. REVIEW CITATIONS
Recent Discussions
This paper has been referenced on Twitter 17 times over the past 90 days. VIEW TWEETS
37 Citations
35 References
Similar Papers

Citations

Publications citing this paper.
Showing 1-10 of 37 extracted citations

57 Citations

02040201620172018
Citations per Year
Semantic Scholar estimates that this publication has 57 citations based on the available data.

See our FAQ for additional information.

References

Publications referenced by this paper.
Showing 1-10 of 35 references

A

  • A. Hannun, C. Case, +6 authors S. Sengupta
  • Coates, et al., “Deep speech: Scaling up end-to…
  • 2014
Highly Influential
10 Excerpts

Listen

  • W. Chan, N. Jaitly, Q. Le, O. Vinyals
  • attend and spell: A neural network for large…
  • 2016
3 Excerpts

Similar Papers

Loading similar papers…