What kind of pronunciation variation is hard for triphones to model?

Dan Jurafsky, Wayne H. Ward, Zhang Banping, Keith Herold, Xiuyang Yu, Zhang Sen

Abstract

In order to help understand why gains in pronunciation modeling have proven so elusive, we investigated which kinds of pronunciation variation are well captured by triphone models, and which are not. We do this by examining the change in behavior of a recognizer as it receives further triphone training. We show that many of the kinds of variation which previous pronunciation models attempt to capture, including phone substitution or phone reduction, are in fact already well captured by triphones. Our analysis suggests new areas where future pronunciation models should focus, including syllable deletion.
BibTeX
@inproceedings{jurafsky2001what,
  author = {Dan Jurafsky and Wayne H. Ward and Zhang Banping and Keith Herold and Xiuyang Yu and Zhang Sen},
  title = {{What kind of pronunciation variation is hard for triphones to model?}},
  booktitle = {IEEE International Conference on Acoustics, Speech and Signal Processing},
  year = {2001},
  doi = {10.1109/icassp.2001.940897},
}

Loading related content...

Figure