Articulatory feature recognition using dynamic Bayesian networks

J. Frankel; M. Wester; S. King

Articulatory feature recognition using dynamic Bayesian networks

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

This paper describes the use of dynamic Bayesian networks for the task of articulatory feature recognition. We show that by modeling the dependencies between a set of 6 multi-leveled articulatory features, recognition accuracy is increased over an equivalent system in which features are considered independent. Results are compared to those found using artificial neural networks on an identical task.

Original language	English
Title of host publication	Interspeech 2004 - ICSLP
Subtitle of host publication	8th International Conference on Spoken Language Processing
Publisher	International Speech Communication Association
Pages	1477-1480
Number of pages	4
ISBN (Print)	ISSN: 1990-9772
Publication status	Published - 1 Sept 2004

Graphical models for automatic speech recognition
King, S. (Principal Investigator)
EPSRC
1/04/04 → 31/08/04
Project: Research
ASR using loosely-coupled HMMs with articulatory- acoustic features
King, S. (Principal Investigator)
UK central government bodies/local authorities, health and hospital authorities
1/01/04 → 29/02/12
Project: Research
Espresso-II: SWITCHING LINEAR DYNAMIC SPEECH MODELS
King, S. (Principal Investigator)
EPSRC
1/07/03 → 30/06/06
Project: Research

Cite this

@inproceedings{78fa6a30b22349b6abaa0d20e0423cb3,

title = "Articulatory feature recognition using dynamic Bayesian networks",

abstract = "This paper describes the use of dynamic Bayesian networks for the task of articulatory feature recognition. We show that by modeling the dependencies between a set of 6 multi-leveled articulatory features, recognition accuracy is increased over an equivalent system in which features are considered independent. Results are compared to those found using artificial neural networks on an identical task.",

author = "J. Frankel and M. Wester and S. King",

note = "ISSN: 1990-9772",

year = "2004",

month = sep,

day = "1",

language = "English",

isbn = "ISSN: 1990-9772",

pages = "1477--1480",

booktitle = "Interspeech 2004 - ICSLP",

publisher = "International Speech Communication Association",

}

TY - GEN

T1 - Articulatory feature recognition using dynamic Bayesian networks

AU - Frankel, J.

AU - Wester, M.

AU - King, S.

N1 - ISSN: 1990-9772

PY - 2004/9/1

Y1 - 2004/9/1

N2 - This paper describes the use of dynamic Bayesian networks for the task of articulatory feature recognition. We show that by modeling the dependencies between a set of 6 multi-leveled articulatory features, recognition accuracy is increased over an equivalent system in which features are considered independent. Results are compared to those found using artificial neural networks on an identical task.

AB - This paper describes the use of dynamic Bayesian networks for the task of articulatory feature recognition. We show that by modeling the dependencies between a set of 6 multi-leveled articulatory features, recognition accuracy is increased over an equivalent system in which features are considered independent. Results are compared to those found using artificial neural networks on an identical task.

M3 - Conference contribution

SN - ISSN: 1990-9772

SP - 1477

EP - 1480

BT - Interspeech 2004 - ICSLP

PB - International Speech Communication Association

ER -

Articulatory feature recognition using dynamic Bayesian networks

Abstract

Fingerprint

Projects

Graphical models for automatic speech recognition

ASR using loosely-coupled HMMs with articulatory- acoustic features

Espresso-II: SWITCHING LINEAR DYNAMIC SPEECH MODELS

Cite this