Speech Recognition by Composition of Weighted Finite Automata

Thumbnail Image

Date

Authors

Journal Title

Journal ISSN

Volume Title

Publisher

Abstract

Description

We 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.
24 pages, uses psfig.sty

Keywords

Computation and Language

Citation

URI

http://salesiana.dossiersoluciones.com/handle/123456789/151265

Consulte el texto completo en el siguiente enlace:

https://arxiv.org/abs/cmp-lg/9603001
 http://arxiv.org/abs/cmp-lg/9603001

Collections

arXiv