Phoneme HMMs constrained by frame correlations
- 1 January 1993
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 2, 219-222 vol.2
- https://doi.org/10.1109/icassp.1993.319274
Abstract
Phoneme HMMs (hidden Markov models) that use correlations between two frames are proposed. The proposed technique constrains the output probability distributions of speaker-independent HMMs so that they are suitable for the input speaker. The speaker-dependent BC (bigram-constrained)-HMMs and speaker-independent BC-HMMs are generated from the conventional speaker-independent HMMs by combining the VQ (vector quantization)-code bigram (discrete case and tied-mixture case) or the conditional Gaussian density function (continuous case). The new models were evaluated by 23-phoneme recognition in continuous speech. In the speaker-dependent BC-HMMs, which use the speaker-dependent bigram created by 50 additional sentences of the test speaker, the best recognition accuracy of 74.8% was obtained by the tied-mixture type BC-HMMs. In the speaker-independent BC-HMMs, the best recognition accuracy of 67.5% was obtained by the continuous type BC-HMMs.<>Keywords
This publication has 5 references indexed in Scilit:
- Explicit time correlation in hidden Markov models for speech recognitionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2005
- Phoneme HMM evaluation algorithm without phoneme labeling applied to continuous speech hmm evaluationElectronics and Communications in Japan (Part III: Fundamental Electronic Science), 1994
- Phonemic HMM constrained by statistical VQ-code transitionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1992
- The Lincoln tied-mixture HMM continuous speech recognizerPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1991
- The Acoustic-Modeling Problem in Automatic Speech Recognition.Published by Defense Technical Information Center (DTIC) ,1987