Abstract
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 language | English |
---|---|
Pages (from-to) | 1408-1409 |
Number of pages | 2 |
Journal | Electronics Letters |
Volume | 41 |
Issue number | 25 |
DOIs | |
Publication status | Published - 1 Dec 2005 |