Welcome!
To use the personalized features of this site, please log in or register.
If you have forgotten your username or password, we can help.
My Menu
Marked Items 
Alerts
Order History
Saved Items
All
Favorites
    
Book Chapter Printable view
Large Vocabulary Continuous Speech Recognition Using Weighted Finite-State Transducers

Large Vocabulary Continuous Speech Recognition Using Weighted Finite-State Transducers

Book SeriesLecture Notes in Computer Science
PublisherSpringer Berlin / Heidelberg
ISSN0302-9743 (Print) 1611-3349 (Online)
VolumeVolume 2389/2002
BookAdvances in Natural Language Processing
DOI10.1007/3-540-45433-0
Copyright2002
ISBN978-3-540-43829-8
DOI10.1007/3-540-45433-0_15
Pages191-214
Subject CollectionComputer Science
SpringerLink DateTuesday, January 01, 2002
Add to marked items

Large Vocabulary Continuous Speech Recognition Using Weighted Finite-State Transducers

Diamantino Caseiro3 Contact Information and Isabel Trancoso3 Contact Information

(3)  INESC-ID/IST, Rua Alves Redol 9, Lisbon, Portugal
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.

Contact Information Diamantino Caseiro
Email: dcaseiro@l2f.inesc-id.pt

Contact Information Isabel Trancoso
Email: Isabel.Trancoso@l2f.inesc-id.pt
Fulltext Preview (Small, Large)
Image of the first page of the fulltext

References secured to subscribers.
more options
Find


Export this chapter
Export this chapter as RIS | Text
 
Frequently asked questions | General information on journals and books | Send us your feedback | Impressum | Contact
© Springer. Part of Springer Science+Business Media
Privacy, Disclaimer, Terms and Conditions, © Copyright Information
Remote Address: 38.107.191.108 • Server: mpweb04
HTTP User Agent: CCBot/1.0 (+http://www.commoncrawl.org/bot.html)