High performance connected digit recognition using maximum mutual information estimation
- 1 January 1991
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 533-536 vol.1
- https://doi.org/10.1109/icassp.1991.150394
Abstract
The authors describe the latest development by the speech research group at CRIM (Centre de Recherche Informatique de Montreal) in speaker-independent connected digit recognition, using hidden Markov Models (HMMs) trained with maximum mutual information estimation, in conjunction with connectionist models. The experiments described were all done on the complete adult portion of the 10 kHz speaker-independent TI/NIST connected digit database. The baseline system, using discrete HMMs and maximum likelihood estimation, has a 98.6% word recognition rate and a 96.1% string recognition rate. The authors describe techniques that made it possible to improve greatly the baseline system recognition rate. The 99.3% recognition rate and 98.0% string recognition rate were obtained with a single model per unit using discrete HMMs and recurrent neural networks. Using semi-continuous HMMs with two models per digit (one for male and one for female speakers), a 99.5% word recognition rate and a 98.4% string recognition rate were achieved.Keywords
This publication has 13 references indexed in Scilit:
- A database for speaker-independent digit recognitionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2005
- Connectionist Viterbi training: a new hybrid method for continuous speech recognitionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- A hybrid coder for hidden Markov models using a recurrent neural networksPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Large vocabulary recognition using linked predictive neural networksPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- An auditory model based on the analysis of envelope patternsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- An improved MMIE training algorithm for speaker-independent, small vocabulary, continuous speech recognitionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1991
- Tied mixture continuous parameter modeling for speech recognitionIEEE Transactions on Acoustics, Speech, and Signal Processing, 1990
- Links between Markov models and multilayer perceptronsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1990
- High performance connected digit recognition using hidden Markov modelsIEEE Transactions on Acoustics, Speech, and Signal Processing, 1989
- Parallel Algorithms for Syllable Recognition in Continuous SpeechPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1985