Edinburgh Research Explorer

A Hybrid ANN/DBN Approach to Articulatory Feature Recognition

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Related Edinburgh Organisations

Open Access permissions

Open

Documents

  • Download as Adobe PDF

    Accepted author manuscript, 149 KB, PDF document

    Licence: Creative Commons: Attribution No Derivatives (CC-BY-ND)

  • Download as Adobe PDF

    191 KB, PDF document

    Licence: Creative Commons: Attribution No Derivatives (CC-BY-ND)

Original languageEnglish
Title of host publicationInterspeech 2005 - Eurospeech
Subtitle of host publication9th European Conference on Speech Communication and Technology
PublisherInternational Speech Communication Association
Pages3045-3048
Number of pages4
ISBN (Print)1990-9772
Publication statusPublished - 1 Sep 2005

Abstract

Artificial neural networks (ANN) have proven to be well suited to the task of articulatory feature (AF) recognition. Previous studies have taken a cascaded approach where separate ANNs are trained for each feature group, making the assumption that features are statistically independent. We address this by using ANNs to provide virtual evidence to a dynamic Bayesian network (DBN). This gives a hybrid ANN/DBN model and allows modelling of inter-feature dependencies. We demonstrate significant increases in AF recognition accuracy from modelling dependencies between features, and present the results of embedded training experiments in which a set of asynchronous feature changes are learned. Furthermore, we report on the application of a Viterbi training scheme in which we alternate between realigning the AF training labels and retraining the ANNs.

Download statistics

No data available

ID: 2077590