Weighted Finite-State Transducers in Speech Recognition (2001)
Cached
Download Links
- [www.research.att.com]
- [www.research.att.com]
- DBLP
Other Repositories/Bibliography
by
Mehryar Mohri
,
Fernando Pereira
,
Michael Riley
| Citations: | 101 - 3 self |
BibTeX
@MISC{Mohri01weightedfinite-state,
author = {Mehryar Mohri and Fernando Pereira and Michael Riley},
title = {Weighted Finite-State Transducers in Speech Recognition},
year = {2001}
}
Years of Citing Articles
Bookmark
 |
 |
 |
 |
 |
 |
OpenURL
Abstract
We survey the use of weighted finite-state transducers (WFSTs) in speech recognition. We show that WFSTs provide a common and natural representation for HMM models, context-dependency, pronunciation dictionaries, grammars, and alternative recognition outputs. Furthermore, general transducer operations combine these representations flexibly and efficiently. Weighted
