E. Eide, B. Maison, et al.
ICSLP 2000
In this paper, we report on speech recognition experi ments with an n-multigram language model, a stochastic model which assumes dependencies of length n between variable-length phrases. The n-multigram probabilities can be estimated in a class-based framework, where both the phrase distribution and the phrase classes are learned from the data according to a Maximum Likeihood cri terion, using a generalized Expectation-Maxiization al gorithm. In our speech recognition experiments on a database of air travel reservations, the 2-multigram mode allows a redction of 10% of the word error rate with respect to the usual trigram model, with 25% fewer param eters than in the trigram mode. We also report on a scheme where some a priori information is introduced in the odel ia seantic tagging.
E. Eide, B. Maison, et al.
ICSLP 2000
S. Dharanipragada, Martin Franz, et al.
ICSLP 2000
Liqin Shen, Guokang Fu, et al.
ICSLP 2000
Sabine Deligne, Ellen Eide, et al.
INTERSPEECH - Eurospeech 2001