Speaker-independent large vocabulary word recognition using an LVQ/HMM hybrid algorithm
- 1 January 1991
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 553-556 vol.1
- https://doi.org/10.1109/icassp.1991.150399
Abstract
An LVQ-HMM (learning vector quantization/hidden Markov model) hybrid algorithm was evaluated. For this evaluation, large vocabulary (5240 word) Japanese word recognition and Japanese phrase recognition were examined. Experiments in both a speaker-dependent and a speaker-independent mode were conducted. Comparison with conventional HMMs showed that LVQ-HMM improved recognition rates for words and phrases as well as for phonemes. In the speaker-dependent mode, LVQ-HMM yielded clear increases in word/phrase recognition accuracy; improvements in the recognition rates ranged between 0.8% and 4.3%. In the speaker-independent mode, however, increases in the word/phrase accuracy were small, but the results suggested some points for further study, e.g., an increase of 8% in recognition rate was achieved for one of the unknown (test) speakers, and LVQ-HMM seemed particularly effective in improving the performance for the test speakers on which conventional HMMs performed poorly.Keywords
This publication has 13 references indexed in Scilit:
- BYBLOS: The BBN continuous speech recognition systemPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2005
- Speaker-independent word recognition using dynamic programming neural networksPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2003
- Large-vocabulary speaker-independent continuous speech recognition using HMMPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2003
- New discriminative training algorithms based on the generalized probabilistic descent methodPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- A new HMM/LVQ hybrid algorithm for speech recognitionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Speaker-independent vowel classification using hidden Markov models and LVQ2Published by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- A hybrid speech recognition system using HMMs with an LVQ-trained codebookPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- ATR HMM-LR continuous speech recognition systemPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- A hybrid speech recognition system using HMMs with an LVQ-trained codebook.Acoustical Science and Technology, 1990
- Statistical pattern recognition with neural networks: benchmarking studiesPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1988