Inter-word coarticulation modeling and MMIE training for improved connected digit recognition
- 1 January 1993
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 2, 243-246 vol.2
- https://doi.org/10.1109/icassp.1993.319280
Abstract
The authors describe developments by the speech research group at CRIM (Centre de Recherche Informatique de Montreal), in the field of speaker-independent connected digit recognition, using hidden Markov models (HMMs) trained with maximum mutual information estimation (MMIE). The experiments described were all performed on the complete adult portion of the TIDIGITS corpus. Techniques that made it possible to improve greatly the recognition rate are described. New results include a 0.28% word error rate and a 0.84% string error rate with two models per digit (one for male and one for female speakers) using context-dependent discrete HMMs.Keywords
This publication has 3 references indexed in Scilit:
- Improved acoustic modeling with Bayesian learningPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1992
- High performance connected digit recognition using codebook exponentsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1992
- High performance connected digit recognition using maximum mutual information estimationPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1991