Continuous mixture densities and linear discriminant analysis for improved context-dependent acoustic models
- 1 January 1993
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 2 (15206149) , 648-651 vol.2
- https://doi.org/10.1109/icassp.1993.319393
Abstract
Linear discriminant analysis (LDA) experiments reported previously (ICASSP-92 vol.1, p.13-16), are extended to context-dependent models and speaker-independent large vocabulary continuous speech recognition. Two variants of using mixture densities are compared: state-specific modeling and the monophone-tying approach where densities are shared across the states relevant to the same phoneme. Results are presented on the DARPA Resource Management (RM) task for both speaker-dependent (SD) and speaker-independent (SI) parts. Using triphone models based on LDA and continuous mixture densities, significant improvements have been observed and the following word error rates have been achieved: for the SD part, 7.8% without grammar and 1.5% with word pair; and for the SI part, 17.2% and 4.6%, respectively. These scores are averaged over 1200 SD or SI evaluation sentences and are among the best published so far on the RM database.Keywords
This publication has 5 references indexed in Scilit:
- The Lincoln robust continuous speech recognizerPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2003
- Experiments on mixture-density phoneme-modelling for the speaker-independent 1000-word speech recognition DARPA taskPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Linear discriminant analysis for improved large vocabulary continuous speech recognitionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1992
- Semi-continuous hidden Markov models for speech signalsComputer Speech & Language, 1989
- Recognition of Isolated Digits Using Hidden Markov Models With Continuous Mixture DensitiesAT&T Technical Journal, 1985