ScienceDirect® Home Skip Main Navigation Links
You have guest access to ScienceDirect. Find out more.
 
Home
Browse
My Settings
Alerts
Help
 Quick Search
 Search tips (Opens new window)
    Clear all fields    
advertisementadvertisement
Speech Communication
Volume 22, Issues 2-3, August 1997, Pages 93-111
 
Font Size: Decrease Font Size  Increase Font Size
 Abstract - selected
Purchase PDF (1797 K)

 
 
 
Related Articles in ScienceDirect
View More Related Articles
 
View Record in Scopus
 
doi:10.1016/S0167-6393(97)00018-6    How to Cite or Link Using DOI (Opens New Window)
Copyright © 1997 Elsevier B.V. All rights reserved.

Production models as a structural basis for automatic speech recognition

L. DengCorresponding Author Contact Information, a, Corresponding Author Contact Information, E-mail The Corresponding Author, G. Ramsaya and D. Sunb

a Department of Electrical and Computer Engineering, University of Waterloo, Waterloo, Ont. N2L 3G1, Canada b Bell Laboratories, Murray Hill, NJ, USA

Received 4 October 1996; 
Revised 17 March 1997; 
accepted 28 April 1997. 
Available online 12 May 1998.

Purchase the full-text article



References and further reading may be available for this article. To view references and further reading you must purchase this article.

Abstract

We postulate in this paper that highly structured speech production models will have much to contribute to the ultimate success of speech recognition in view of the weaknesses of the theoretical foundation underpinning current technology. These weaknesses are analyzed in terms of phonological modeling and of phonetic-interface modeling. We present two probabilistic speech recognition models with the structure designed based on approximations to human speech production mechanisms, and conclude by suggesting that many of the advantages to be gained from interaction between speech production and speech recognition communities will develop from integrating production models with the probabilistic analysis-by-synthesis strategy currently used by the technology community.

Résumé

Dans cet article, nous suggérons que des modèles de production de la parole fortement structurés pourront contribuer significativement à la réussite future des modèles de reconnaissance automatique de la parole, limités en ce moment par les faiblesses de la base théorique de la technologie actuelle. Nous analysons ces faiblesses au niveau des modèles phonologiques et des modèles phonétiques, et présentons deux modèles statistiques de reconnaissance de la parole basés sur des approximations des mécanismes de production de la parole. Nous suggérons en conclusion que l'interaction entre les domaines de la production et de la reconnaissance de la parole peut être particulièrement efficace si l'on intègre les modèles de production dans la stratégie d'analyse-synthèse probabiliste, utilisée déjà depuis longtemps en reconnaissance de la parole.

Author Keywords: Speech production; Speech recognition; Analysis by synthesis; Stochastic modeling; Nonlinear phonology; Phonetic interface; Articulatory features; Articulatory dynamics; Stochastic target model

Article Outline

• Further Reading

Speech Communication
Volume 22, Issues 2-3, August 1997, Pages 93-111
 
Home
Browse
My Settings
Alerts
Help
Elsevier.com (Opens new window)
About ScienceDirect  |  Contact Us  |  Information for Advertisers  |  Terms & Conditions  |  Privacy Policy
Copyright © 2008 Elsevier B.V. All rights reserved. ScienceDirect® is a registered trademark of Elsevier B.V.