A fast segmental Viterbi algorithm for large vocabulary recognition
- 19 November 2002
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 1 (15206149) , 560-563 vol.1
- https://doi.org/10.1109/icassp.1995.479659
Abstract
The paper presents a fast segmental Viterbi algorithm. A new search strategy particularly effective for very large vocabulary word recognition. It performs a tree based, time synchronous, left-to-right beam search that develops time-dependent acoustic and phonetic hypotheses. At any given time, it makes active a sub-word unit associated to an arc of a lexical tree only if that time is likely to be the boundary between the current and the next unit. This new technique, tested with a vocabulary of 188892 directory entries, achieves the same results obtained with the Viterbi algorithm, with a 35% speedup. Results are also presented for a 718 word, speaker independent continuous speech recognition task.Keywords
This publication has 4 references indexed in Scilit:
- Large vocabulary word recognition based on tree-trellis searchPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Using grammars in forward and backward searchPublished by International Speech Communication Association ,1993
- A*-admissible heuristics for rapid lexical accessIEEE Transactions on Speech and Audio Processing, 1993
- A look-ahead search technique for large vocabulary continuous speech recognitionPublished by International Speech Communication Association ,1991