Articulatory feature recognition using dynamic Bayesian networks

Authors:
Joe Frankel;Mirjam Wester;Simon King
Affiliations:
Centre for Speech Technology Research, University of Edinburgh, 2 Buccleuch Place, Edinburgh EH8 9LW, UK;Centre for Speech Technology Research, University of Edinburgh, 2 Buccleuch Place, Edinburgh EH8 9LW, UK;Centre for Speech Technology Research, University of Edinburgh, 2 Buccleuch Place, Edinburgh EH8 9LW, UK
Venue:
Computer Speech and Language
Year:
2007

Citing 7
Cited 8

Maximum-likelihood continuity mapping (MALCOM): an alternative to HMMs

Proceedings of the 1998 conference on Advances in neural information processing systems II
Bayesian Networks and Decision Graphs

Bayesian Networks and Decision Graphs
Connectionist speech recognition of Broadcast News

Speech Communication - Special issue on automatic transcription of broadcast news data
A syllable, articulatory-feature, and stress-accent model of speech recognition

A syllable, articulatory-feature, and stress-accent model of speech recognition
The HDM: a segmental hidden dynamic model of coarticulation

ICASSP '99 Proceedings of the Acoustics, Speech, and Signal Processing, 1999. on 1999 IEEE International Conference - Volume 01
Distinctive feature detection using support vector machines

ICASSP '99 Proceedings of the Acoustics, Speech, and Signal Processing, 1999. on 1999 IEEE International Conference - Volume 01
CasJoin: a cascade chain for text similarity joins

CIKM '10 Proceedings of the 19th ACM international conference on Information and knowledge management

A study on integrating acoustic-phonetic information into lattice rescoring for automatic speech recognition

Speech Communication
Review: Statistical parametric speech synthesis

Speech Communication
A conditional independence algorithm for learning undirected graphical models

Journal of Computer and System Sciences
Discriminative input stream combination for conditional random field phone recognition

IEEE Transactions on Audio, Speech, and Language Processing
Integrating phonological knowledge in ASR systems for Spanish language

CIARP'10 Proceedings of the 15th Iberoamerican congress conference on Progress in pattern recognition, image analysis, computer vision, and applications
Improving articulatory feature and phoneme recognition using multitask learning

ICANN'11 Proceedings of the 21th international conference on Artificial neural networks - Volume Part I
Automatic analysis of Mandarin accented English using phonological features

Speech Communication
Exploiting deep neural networks for detection-based speech recognition

Neurocomputing

Quantified Score

Hi-index	0.00

Visualization

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.