Repository logo
 
Publication

Enhancing Multimodal Silent Speech Interfaces With Feature Selection

2014Conference object Restricted access
Simple item page
dc.contributor.authorFreitas, João
dc.contributor.authorJ. Ferreira, Artur
dc.contributor.authorFigueiredo, Mário Alexandre Teles de
dc.contributor.authorTeixeira, António
dc.contributor.authorDias, Miguel Sales
dc.date.accessioned2015-08-18T11:37:56Z
dc.date.available2015-08-18T11:37:56Z
dc.date.issued2014
dc.description.abstractIn research on Silent Speech Interfaces (SSI), different sources of information (modalities) have been combined, aiming at obtaining better performance than the individual modalities. However, when combining these modalities, the dimensionality of the feature space rapidly increases, yielding the well-known "curse of dimensionality". As a consequence, in order to extract useful information from this data, one has to resort to feature selection (FS) techniques to lower the dimensionality of the learning space. In this paper, we assess the impact of FS techniques for silent speech data, in a dataset with 4 non-invasive and promising modalities, namely: video, depth, ultrasonic Doppler sensing, and surface electromyography. We consider two supervised (mutual information and Fisher's ratio) and two unsupervised (meanmedian and arithmetic mean geometric mean) FS filters. The evaluation was made by assessing the classification accuracy (word recognition error) of three well-known classifiers (knearest neighbors, support vector machines, and dynamic time warping). The key results of this study show that both unsupervised and supervised FS techniques improve on the classification accuracy on both individual and combined modalities. For instance, on the video component, we attain relative performance gains of 36.2% in error rates. FS is also useful as pre-processing for feature fusion. Copyright © 2014 ISCA.por
dc.identifier.citationFREITAS, João; [et al] – Enhancing multimodal silent speech interfaces with feature selection. In Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH. ISCA - International Speech and Communication Association, 2014. ISSN: 2308-457X. p. 1169-1173.
dc.identifier.issn2308-457X
dc.identifier.urihttp://hdl.handle.net/10400.21/4803
dc.language.isoengpor
dc.peerreviewedyespor
dc.publisherISCA - International Speech and Communication Associationpor
dc.relationMarie Curie IRIS 610986, FP7-PEOPLE-2013-IAPP
dc.relationMarie Curie Golem ref.251415, FP7-PEOPLE-2009-IAPP
dc.relationFCOMP-01-0124-FEDER-022682
dc.relationFCT-PEstC/EEI/UI0127/2011
dc.subjectFeature Selectionpor
dc.subjectMultimodal Silent Speech Interfacepor
dc.subjectSupervised Classificationpor
dc.titleEnhancing Multimodal Silent Speech Interfaces With Feature Selectionpor
dc.typeconference object
dspace.entity.typePublication
oaire.citation.endPage1173por
oaire.citation.startPage1169por
oaire.citation.titleProceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECHpor
person.familyNameFerreira
person.givenNameArtur
person.identifier1049438
person.identifier.ciencia-id091A-96FB-A88C
person.identifier.orcid0000-0002-6508-0932
person.identifier.ridAAL-4377-2020
person.identifier.scopus-author-id35315359300
rcaap.rightsclosedAccesspor
rcaap.typeconferenceObjectpor
relation.isAuthorOfPublication734bfe75-0c68-4cdf-8a87-2aef3564f5bd
relation.isAuthorOfPublication.latestForDiscovery734bfe75-0c68-4cdf-8a87-2aef3564f5bd

Files

Original bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
Enhancing multimodal silent speech.pdf
Size:
177.83 KB
Format:
Adobe Portable Document Format
Download
License bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
license.txt
Size:
1.71 KB
Format:
Item-specific license agreed upon to submission
Description:
Download

Collections

ISEL - Eng. Elect. Tel. Comp. - Comunicações