ISCA Archive ICSLP 1994
ISCA Archive ICSLP 1994

MMIE training for large vocabulary continuous speech recognition

Yves Normandin, Roxane Lacouture, Regis Cardin

Over the past few years, there have been several published reports on the use of MMIE (Maximum Mutual Information Estimation) for training HMM parameters. Many of these reports clearly demonstrate MMIE's capability of substantially reducing the error rate in certain types speech recognition applications. The most convincing demonstrations, however, have usually been carried out on either small vocabulary tasks or on isolated speech. This is in large part a consequence of the fact that, for large vocabularies, MMIE training is much too computationally expensive and approximations must therefore be found in order to bring the task down to a manageable size. This paper looks at such approximations which can be applied in the context of large vocabulary continuous speech recognition and, in particular, proposes a technique based on the use of a compact looped word lattice. Experiments are used to demonstrate the effectiveness of the technique.


Cite as: Normandin, Y., Lacouture, R., Cardin, R. (1994) MMIE training for large vocabulary continuous speech recognition. Proc. 3rd International Conference on Spoken Language Processing (ICSLP 1994), 1367-1370

@inproceedings{normandin94_icslp,
  author={Yves Normandin and Roxane Lacouture and Regis Cardin},
  title={{MMIE training for large vocabulary continuous speech recognition}},
  year=1994,
  booktitle={Proc. 3rd International Conference on Spoken Language Processing (ICSLP 1994)},
  pages={1367--1370}
}