Informatics Report Series


Report   

EDI-INF-RR-1039


Related Pages

Report (by Number) Index
Report (by Date) Index
Author Index
Institute Index

Home
Title:Articulatory feature recognition using dynamic Bayesian networks
Authors: Jolyon Frankel ; Simon King ; Mirjam Wester
Date:Oct 2007
Publication Title:Computer Speech and Language
Publisher:Elsevier
Publication Type:Journal Article Publication Status:Published
Volume No:21(4) Page Nos:620-640
DOI:10.1016/j.csl.2007.03.002 ISBN/ISSN:0885-2308
Abstract:
We describe a dynamic Bayesian network for articulatory feature recognition. The model is intended to be a component of a speech recognizer that avoids the problems of conventional ``beads-on-a-string'' phoneme-based models. We demonstrate that the model gives superior recognition of articulatory features from the speech signal compared with a state-of-the art neural network system. We also introduce a training algorithm that offers two major advances: it does not require time-aligned feature labels and it allows the model to learn a set of asynchronous feature changes in a data-driven manner.
Copyright:
2007 by The University of Edinburgh. All Rights Reserved
Links To Paper
No links available
Bibtex format
@Article{EDI-INF-RR-1039,
author = { Jolyon Frankel and Simon King and Mirjam Wester },
title = {Articulatory feature recognition using dynamic Bayesian networks},
journal = {Computer Speech and Language},
publisher = {Elsevier},
year = 2007,
month = {Oct},
volume = {21(4)},
pages = {620-640},
doi = {10.1016/j.csl.2007.03.002},
}


Home : Publications : Report 

Please mail <reports@inf.ed.ac.uk> with any changes or corrections.
Unless explicitly stated otherwise, all material is copyright The University of Edinburgh