Feature-based pronunciation modeling for automatic speech recognition

@inproceedings{Livescu2005FeaturebasedPM,
  title={Feature-based pronunciation modeling for automatic speech recognition},
  author={Karen Livescu},
  year={2005}
}
ƒ Contributions: • Introduction of a general, flexible featurebased pronunciation model, accounting for feature asynchrony and feature substitutions • Implementation using dynamic Bayesian networks • Initial experiments on spontaneous pronunciations Karen Livescu and James Glass Spoken Language Systems Group, MIT Computer Science and Artificial Intelligence Laboratory, Cambridge MA 02139 USA {klivescu,jrg}@sls.csail.mit.edu, http://www.sls.csail.mit.edu/{livescu,glass} 6/6 

Citations

Publications citing this paper.
SHOWING 1-10 OF 37 CITATIONS

References

Publications referenced by this paper.

Similar Papers

Loading similar papers…