Utilize este identificador para referenciar este registo: http://hdl.handle.net/10400.21/4803
Título: Enhancing Multimodal Silent Speech Interfaces With Feature Selection
Autor: Freitas, João
Ferreira, Artur Jorge
Figueiredo, Mário Alexandre Teles de
Teixeira, António
Dias, Miguel Sales
Palavras-chave: Feature Selection
Multimodal Silent Speech Interface
Supervised Classification
Data: 2014
Editora: ISCA - International Speech and Communication Association
Citação: FREITAS, 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.
Resumo: In 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.
Peer review: yes
URI: http://hdl.handle.net/10400.21/4803
ISSN: 2308-457X
Aparece nas colecções:ISEL - Eng. Elect. Tel. Comp. - Comunicações

Ficheiros deste registo:
Ficheiro Descrição TamanhoFormato 
Enhancing multimodal silent speech.pdf177,83 kBAdobe PDFVer/Abrir    Acesso Restrito. Solicitar cópia ao autor!


FacebookTwitterDeliciousLinkedInDiggGoogle BookmarksMySpace
Formato BibTex MendeleyEndnote Degois 

Todos os registos no repositório estão protegidos por leis de copyright, com todos os direitos reservados.