Improving WFST-based G2P Conversion with Alignment Constraints and RNNLM N-best Rescoring

@inproceedings{Novak2012ImprovingWG,
  title={Improving WFST-based G2P Conversion with Alignment Constraints and RNNLM N-best Rescoring},
  author={Josef R. Novak and Nobuaki Minematsu and Keikichi Hirose and Chiori Hori and Hideki Kashioka and Paul R. Dixon},
  booktitle={INTERSPEECH},
  year={2012}
}
This work introduces a modified WFST-based multiple to multiple EM-driven alignment algorithm for Graphemeto-Phoneme (G2P) conversion, and preliminary experimental results applying a Recurrent Neural Network Language Model (RNNLM) as an N-best rescoring mechanism for G2P conversion. The alignment algorithm leverages the WFST framework and introduces several simple structural constraints which yield a small but consistent improvement in Word Accuracy (WA) on a selection of standard baselines… CONTINUE READING
Highly Cited
This paper has 41 citations. REVIEW CITATIONS

Citations

Publications citing this paper.
Showing 1-10 of 28 extracted citations

References

Publications referenced by this paper.

Similar Papers

Loading similar papers…