Authors
Mehryar Mohri, Fernando Pereira, Michael Riley
Publication date
2002/1/1
Journal
Computer Speech & Language
Volume
16
Issue
1
Pages
69-88
Publisher
Academic Press
Description
We survey the use of weighted finite-state transducers (WFSTs) in speech recognition. We show that WFSTs provide a common and natural representation for hidden Markov models (HMMs), 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 40 000 words, and a large trigram grammar into a single weighted transducer that is only somewhat larger than the trigram …
Total citations
Scholar articles
M Mohri, F Pereira, M Riley - Computer Speech & Language, 2002