Towards Phonetically-Driven Hidden Markov Models: Can We Incorporate Phonetic Landmarks in HMM-Based ASR?

@inproceedings{Gravier2007TowardsPH,
  title={Towards Phonetically-Driven Hidden Markov Models: Can We Incorporate Phonetic Landmarks in HMM-Based ASR?},
  author={Guillaume Gravier and Daniel Moraru},
  booktitle={NOLISP},
  year={2007}
}
Automatic speech recognition mainly relies on hidden Markov models (HMM) which make little use of phonetic knowledge. As an alternative, landmark based recognizers rely mainly on precise phonetic knowledge and exploit distinctive features. We propose a theoretical framework to combine both approaches by introducing phonetic knowledge in a non stationary HMM decoder. To demonstrate the potential of the method, we investigate how broad phonetic landmarks could be used to improve a HMM decoder by… CONTINUE READING
BETA

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

Key Quantitative Results

  • The use of all the classes reduces the error rate from 22% to 14% on a broadcast news transcription task.

References

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

Corpus description of the ES- TER evaluation campaign for the rich transcription of french broadcast news

  • S. Galliano, E. Geoffrois, J.-F. Bonastre, G. Gravier, D. Mostefa, K. Choukri
  • Language Resources and Evaluation Conference, .
  • 2006
1 Excerpt

Nasal landmark detection

  • M. Chen
  • Intl. Conf. Speech and Language Processing, , pp…
  • 2000
2 Excerpts

Similar Papers

Loading similar papers…