A successive state splitting algorithm for efficient allophone modeling
- 1 January 1992
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 1, 573-576 vol.1
- https://doi.org/10.1109/icassp.1992.225855
Abstract
The authors propose an algorithm, successive state splitting (SSS), for simultaneously finding an optimal set of phoneme context classes, an optimal topology, and optimal parameters for hidden Markov models (HMMs) commonly using a maximum likelihood criterion. With this algorithm, a hidden Markov network (HM-Net), which is an efficient representation of phoneme-context-dependent HMMs, can be generated automatically. The authors implemented this algorithm, and tested it on the recognition of six Japanese consonants ( mod b mod , mod d mod , mod g mod , mod m mod , mod n mod and mod N mod ). The HM-Net gave better recognition results with a lower number of total output probability density distributions than conventional phoneme-context-independent mixture Gaussian density HMMs.Keywords
This publication has 5 references indexed in Scilit:
- Context-dependent modeling for acoustic-phonetic recognition of continuous speechPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2005
- Phoneme environment clustering for speech recognitionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2003
- Allophone clustering for continuous speech recognitionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Improved acoustic modeling with the SPHINX speech recognition systemPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1991
- Extending the vocabulary of a speaker independent recognition systemPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1991