The Lincoln tied-mixture HMM continuous speech recognizer
- 1 January 1991
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 15206149,p. 329-332 vol.1
- https://doi.org/10.1109/icassp.1991.150343
Abstract
The Lincoln robust HMM (hidden Markov model) recognizer has been converted from a single Gaussian or Gaussian mixture PDF per state to tied mixtures in which a single set of Gaussians is shared between all states. There were initial difficulties caused by the use of mixture pruning but these were cured by using observation pruning. Fixed weight smoothing of the mixture weights allowed the use of word-boundary-context-dependent triphone models for both speaker-dependent (SD) and speaker-independent (SI) recognition. A second-differential observation stream further improved SI performance but not SD performance. A novel form of phonetic context model, the semiphone, is also introduced. This model significantly reduces the number of states required to model a vocabulary and unifies triphone and diphone modeling.Keywords
This publication has 13 references indexed in Scilit:
- Context-dependent modeling for acoustic-phonetic recognition of continuous speechPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2005
- Tied mixture continuous parameter models for large vocabulary isolated speech recognitionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2003
- Speaker stress-resistant continuous speech recognitionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2003
- Identification of contextual factors for pronunciation networksPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- On vocabulary-independent speech modelingPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Semi-continuous hidden Markov models for speech signalsComputer Speech & Language, 1989
- Automatic Speech RecognitionPublished by Springer Nature ,1989
- Proceedings of the 3rd international conference on Supercomputing - ICS '89Published by Association for Computing Machinery (ACM) ,1989
- The Lincoln Continuous Speech Recognition system: recent developments and resultsPublished by Association for Computational Linguistics (ACL) ,1989
- Tied mixtures in the Lincoln robust CSRPublished by Association for Computational Linguistics (ACL) ,1989