Fast algorithms for phone classification and recognition using segment-based models
- 1 January 1992
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Signal Processing
- Vol. 40 (12) , 2885-2896
- https://doi.org/10.1109/78.175733
Abstract
Methods for reducing the computation requirements of joint segmentation and recognition of phones using the stochastic segment model are presented. The approach uses a fast segment classification method that reduces computation by a factor of two to four, depending on the confidence of choosing the most probable model. A split-and-merge segmentation algorithm is proposed as an alternative to the typical dynamic programming solution of the segmentation and recognition problem, with computation savings increasing proportionally with model complexity. Although the current recognizer uses context-independent phone models, the results reported for the TIMIT database for speaker-independent joint segmentation and recognition are comparable to those of systems that use context informationKeywords
This publication has 17 references indexed in Scilit:
- A stochastic segment model for phoneme-based continuous speech recognitionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2005
- Continuous speech recognition for the TIMIT database using neural networksPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Speaker-independent phone recognition using hidden Markov modelsIEEE Transactions on Acoustics, Speech, and Signal Processing, 1989
- Improvements in the stochastic segment model for Phoneme recognitionPublished by Association for Computational Linguistics (ACL) ,1989
- A stochastic segment model for phoneme-based continuous speech recognitionIEEE Transactions on Acoustics, Speech, and Signal Processing, 1989
- Network-based connected digit recognitionIEEE Transactions on Acoustics, Speech, and Signal Processing, 1987
- Optimization by Simulated AnnealingScience, 1983
- A Maximum Likelihood Approach to Continuous Speech RecognitionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1983
- Picture Segmentation by a Tree Traversal AlgorithmJournal of the ACM, 1976
- Segmentation of Plane CurvesIEEE Transactions on Computers, 1974