ISCA Archive ICSLP 1994
ISCA Archive ICSLP 1994

Modelling syllable characteristics to improve a large vocabulary continuous speech recogniser

M. Jones, Phil C. Woodland

The acoustic-phonetic modelling used in state-of-the-art large vocabulary continuous speech recognisers (LVCSR) cannot effectively exploit the prosody based distinctions known to exist at the syllable level. These distinctions are between the strength of the syllable (strong or weak) and the stress (stressed or unstressed) it is given. This paper shows how a small set of syllable-sized Hidden Markov Models (HMMs) can model syllable type effectively. These models have been applied to a large vocabulary continuous speech recogniser and a 23% reduction in word error rate was achieved.


Cite as: Jones, M., Woodland, P.C. (1994) Modelling syllable characteristics to improve a large vocabulary continuous speech recogniser. Proc. 3rd International Conference on Spoken Language Processing (ICSLP 1994), 2171-2174

@inproceedings{jones94_icslp,
  author={M. Jones and Phil C. Woodland},
  title={{Modelling syllable characteristics to improve a large vocabulary continuous speech recogniser}},
  year=1994,
  booktitle={Proc. 3rd International Conference on Spoken Language Processing (ICSLP 1994)},
  pages={2171--2174}
}