Confidence estimation, OOV detection and language ID using phone-to-word transduction and phone-level alignments

@article{White2008ConfidenceEO,
  title={Confidence estimation, OOV detection and language ID using phone-to-word transduction and phone-level alignments},
  author={Christopher M. White and Geoffrey Zweig and Luk{\'a}s Burget and Petr Schwarz and Hynek Hermansky},
  journal={2008 IEEE International Conference on Acoustics, Speech and Signal Processing},
  year={2008},
  pages={4085-4088}
}
Automatic speech recognition (ASR) systems continue to make errors during search when handling various phenomena including noise, pronunciation variation, and out of vocabulary (OOV) words. Predicting the probability that a word is incorrect can prevent the error from propagating and perhaps allow the system to recover. This paper addresses the problem of detecting errors and OOVs for read Wall Street Journal speech when the word error rate (WER) is very low. It augments a traditional… CONTINUE READING
Highly Cited
This paper has 36 citations. REVIEW CITATIONS

Citations

Publications citing this paper.
Showing 1-10 of 29 extracted citations

Similar Papers

Loading similar papers…