Automatic Editing in a Back-End Speech-to-Text System

@inproceedings{Bisani2008AutomaticEI,
  title={Automatic Editing in a Back-End Speech-to-Text System},
  author={Maximilian Bisani and Paul Vozila and Olivier Divay and Jeff Adams},
  booktitle={ACL},
  year={2008}
}
Written documents created through dictation differ significantly from a true verbatim transcript of the recorded speech. This poses an obstacle in automatic dictation systems as speech recognition output needs to undergo a fair amount of editing in order to turn it into a document that complies with the customary standards. We present an approach that attempts to perform this edit from recognized words to final document automatically by learning the appropriate transformations from example… CONTINUE READING

Similar Papers

Figures, Tables, Results, and Topics from this paper.

Key Quantitative Results

  • With 100 training documents per user the mean token error rate is reduced by up to 40% relative by the probabilistic model.

Citations

Publications citing this paper.

References

Publications referenced by this paper.
SHOWING 1-8 OF 8 REFERENCES

Topic segmentation using Markov models on section level

  • 2003 IEEE Workshop on Automatic Speech Recognition and Understanding (IEEE Cat. No.03EX721)
  • 2003
VIEW 2 EXCERPTS

Statistical models for text segmentation

Beeferman, Doug, Adam Berger, John Lafferty.
  • Machine Learning, 34(1-3):177 – 210.
  • 1999
VIEW 2 EXCERPTS

A fertility channel model for post-correction of continuous speech recognition

  • Proceeding of Fourth International Conference on Spoken Language Processing. ICSLP '96
  • 1996

Combining the detection and correction of speech repairs

  • Proceeding of Fourth International Conference on Spoken Language Processing. ICSLP '96
  • 1996
VIEW 2 EXCERPTS