An improved MMIE training algorithm for speaker-independent, small vocabulary, continuous speech recognition
- 1 January 1991
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 15206149,p. 537-540 vol.1
- https://doi.org/10.1109/icassp.1991.150395
Abstract
Recently, Gopalakrishnan et al. (1989) introduced a reestimation formula for discrete HMMs (hidden Markov models) which applies to rational objective functions like the MMIE (maximum mutual information estimation) criterion. The authors analyze the formula and show how its convergence rate can be substantially improved. They introduce a corrective MMIE training algorithm, which, when applied to the TI/NIST connected digit database, has made it possible to reduce the string error rate by close to 50%. Gopalakrishnan's result is extended to the continuous case by proposing a new formula for estimating the mean and variance parameters of diagonal Gaussian densities.Keywords
This publication has 9 references indexed in Scilit:
- Maximum mutual information estimation of hidden Markov model parameters for speech recognitionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2005
- A generalization of the Baum algorithm to rational objective functionsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2003
- Phonetic recognition using hidden Markov models and maximum mutual information trainingPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2003
- Maximum mutual information estimation of HMM parameters for continuous speech recognition using the N-best algorithmPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- High performance connected digit recognition using maximum mutual information estimationPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1991
- On a model-robust training method for speech recognitionIEEE Transactions on Acoustics, Speech, and Signal Processing, 1988
- The Acoustic-Modeling Problem in Automatic Speech Recognition.Published by Defense Technical Information Center (DTIC) ,1987
- A decision theorectic formulation of a training problem in speech recognition and a comparison of training by unconditional versus conditional maximum likelihoodIEEE Transactions on Acoustics, Speech, and Signal Processing, 1983
- An inequality with applications to statistical estimation for probabilistic functions of Markov processes and to a model for ecologyBulletin of the American Mathematical Society, 1967