Sciweavers

CSL
2002
Springer

Weighted finite-state transducers in speech recognition

13 years 3 months ago
Weighted finite-state transducers in speech recognition
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 determinization and minimization algorithms optimize their time and space requirements, and a weight pushing algorithm distributes the weights along the paths of a weighted transducer optimally for speech recognition. As an example, we describe a North American Business News (NAB) recognition system built using these techniques that combines the HMMs, full cross-word triphones, a lexicon of forty thousand words, and a large trigram grammar into a single weighted transducer that is only somewhat larger than the trigram word grammar and that runs NAB in real-time on a very simple decoder. In another example, we show that the ...
Mehryar Mohri, Fernando Pereira, Michael Riley
Added 18 Dec 2010
Updated 18 Dec 2010
Type Journal
Year 2002
Where CSL
Authors Mehryar Mohri, Fernando Pereira, Michael Riley
Comments (0)