Finite-State Transducers in Language and Speech Processing

OpenFst: An Open-Source, Weighted Finite-State Transducer Library and its Applications to Speech and Language

Finite-state methods are well established in language and speech processing. OpenFst (available from www.openfst.org) is a free and open-source software library for building and using finite automata, in particular, weighted finite-state transducers (FSTs). This tutorial is an introduction to weighted finitestate transducers and their uses in speech and language processing. While there are othe...

Finite-State Transducers

Finite-state transducers play an important role in natural language processing. They provide a model for text and speech, as well as transformations of them. In order to reduce the complexity of their application, deterministic and minimal transducers are required. This essay introduces a particular type of finite-state transducers, subsequential string-to-weight transducers, and presents algor...

Weighted Finite-State Transducers in Speech and Natural Language Processing Solution Set 7: Final Examination

Applying Transducers to Spoken Language Processing for Portuguese

This paper has two different goals. The primary aim is to illustrate the advantages of weighted finite state transducers for spoken language processing, namely in terms of their capacity to efficiently integrate different types of knowledge sources. We have chosen three areas to emphasize several aspects of the application of transducers: large vocabulary continuous speech recognition, automati...

Spoken Language Processing Using Weighted Finite State Transducers

The main goal of this paper is to illustrate the advantages of weighted finite state transducers (WFSTs) for spoken language processing, namely in terms of their capacity to efficiently integrate different types of knowledge sources. We shall illustrate their applicability in several areas: large vocabulary continuous speech recognition, automatic alignment using pronunciation modeling rules, g...