1st ETRW on Speech Production Modeling: From Control Strategies to Acoustics 4th Speech Production Seminar: Models and Data Autrans, France May 20-24, 1996

Production Models as a Structural Basis for Automatic Speech Recognition

L. Deng (1), Gordon Ramsay (1), D. Sun (2)

(1) University of Waterloo, Ontario, Canada
(2) Bell Laboratories, Murray Hill, NJ, USA

In this paper, we argue 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 interface modeling. We conclude by suggesting that many of the advantages to be gained from interaction between speech production and speech recognition communities will develop from integrating models from the production community with the probabilistic analysis-by-synthesis strategy currently used by the technology community.

Full Paper

Bibliographic reference.  Deng, L. / Ramsay, Gordon / Sun, D. (1996): "Production models as a structural basis for automatic speech recognition", In SPM-1996, 69-80.