Large Vocabulary Continuous Speech Recognition Using Weighted Finite-State Transducers

Authors:
Diamantino Caseiro;Isabel Trancoso
Affiliations:
-;-
Venue:
PorTAL '02 Proceedings of the Third International Conference on Advances in Natural Language Processing
Year:
2002

Citing 3
Cited 0

A Rational Design for a Weighted Finite-State Transducer Library

WIA '97 Revised Papers from the Second International Workshop on Implementing Automata
Finite-state transducers in language and speech processing

Computational Linguistics
Real-time telephone-based speech recognition in the Jupiter domain

ICASSP '99 Proceedings of the Acoustics, Speech, and Signal Processing, 1999. on 1999 IEEE International Conference - Volume 01

Quantified Score

Hi-index	0.00

Visualization

Abstract

Weighted finite-state transducers are an unifying formalism for the implementation and integration of the various knowledge sources and structures typical of a large vocabulary continuous speech recognition system.In this work we show how those knowledge sources can be converted to this formalism, and how they can be integrated in an optimized network, using our finite-state library and tools.Experiments performed using our system showed the importance of the optimization of the integrated network, and allowed us to obtain very significant improvements in the speed of the recognizer.