Reducing computational load in segmental hidden Markov model decoding for speech recognition

Research output: Contribution to journalArticle

Colleges, School and Institutes


Segment models have the potential to improve automatic speech recognition accuracy but with increased computational load. Two techniques which reduce this load are described: segmental beam pruning, and duration pruning. Experiments show that they can combine to give a 95% reduction in segment probability computations at a cost of a 3% increase in phone error rate.


Original languageEnglish
Pages (from-to)1408-1409
Number of pages2
JournalElectronics Letters
Issue number25
Publication statusPublished - 1 Dec 2005