Speech Recognition by Composition of Weighted Finite Automata

Simple item page
dc.creatorPereira, Fernando C. N.
dc.creatorRiley, Michael D.
dc.date1996-03-07
dc.date.accessioned2026-07-07T09:10:07Z
dc.date.available2026-07-07T09:10:07Z
dc.descriptionWe present a general framework based on weighted finite automata and weighted finite-state transducers for describing and implementing speech recognizers. The framework allows us to represent uniformly the information sources and data structures used in recognition, including context-dependent units, pronunciation dictionaries, language models and lattices. Furthermore, general but efficient algorithms can used for combining information sources in actual recognizers and for optimizing their application. In particular, a single composition algorithm is used both to combine in advance information sources such as language models and dictionaries, and to combine acoustic observations and information sources dynamically during recognition.
dc.description24 pages, uses psfig.sty
dc.identifierhttps://arxiv.org/abs/cmp-lg/9603001
dc.identifierhttp://arxiv.org/abs/cmp-lg/9603001
dc.identifier.urihttp://salesiana.dossiersoluciones.com/handle/123456789/151265
dc.subjectComputation and Language
dc.titleSpeech Recognition by Composition of Weighted Finite Automata
dc.typetext

Files

Collections

arXiv