Statistical segmentation and word modeling techniques in isolated word recognition
- 4 December 2002
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 745-748 vol.2
- https://doi.org/10.1109/icassp.1990.115898
Abstract
A speech recognition system is described using a combination of statistical segment and word modeling. Segment models are constructed by first segmenting training data automatically and then grouping the resultant segments into clusters. Mixtures of Gaussian densities are used to model each segment cluster. In order to integrate the segment models into word models, a generalization of the hidden Markov model approach is proposed. Experimental results on a multispeaker recognition system for alpha-digits demonstrate that the new approach improved the performance of conventional whole-word-based models. In particular, the word models show good discrimination abilities for differentiating phonetically similar words such as the E-set alphabet.Keywords
This publication has 6 references indexed in Scilit:
- On the automatic segmentation of speech signalsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2005
- A phonetically labeled acoustic segment (PLAS) approach to speech analysis-synthesisPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2003
- On the use of some robust modeling techniques for speech recognitionComputer Speech & Language, 1989
- Some performance benchmarks for isolated work speech recognition systemsComputer Speech & Language, 1987
- Recognition of Isolated Digits Using Hidden Markov Models With Continuous Mixture DensitiesAT&T Technical Journal, 1985
- A method for segmenting acoustic patterns, with applications to automatic speech recognitionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1977