|
Edinburgh Research Archive >
Centre for Speech Technology Research >
CSTR publications >
Please use this identifier to cite or link to this item:
http://hdl.handle.net/1842/978
|
| Title: | Speech recognition via phonetically-featured syllables |
| Authors: | King, Simon
Taylor, Paul
Frankel, Joe
Richmond, Korin |
| Issue Date: | 2000 |
| Citation: | Koreman, J. & Barry, W. J. (eds.) with K. Kirchhoff as guest editor. Proceedings of a Workshop on Phonetics and Phonology in ASR. Parameters and features and their implications. PHONUS 5, Saarbruecken, 2000, pp.15-34 |
| Publisher: | University of the Saarland |
| Abstract: | We describe recent work on two new automatic speech recognition systems. The first part of this paper describes the components of a system based on phonological features (which we call Espresso-P) in which the values of these features are estimated from the speech signal before being used as the basis for recognition. In the second part of the paper, another system (which we call Espresso-A) is described in which articulatory parameters are used instead of phonological features and a linear dynamical system model is used to perform recognition from automatically estimated values of these articulatory parameters. |
| URI: | http://hdl.handle.net/1842/978 |
| Appears in Collections: | CSTR publications
Linguistics and English Language publications
|
Items in ERA are protected by copyright, with all rights reserved, unless otherwise indicated.
|
