Please use this identifier to cite or link to this item:
http://hdl.handle.net/10071/25831
Author(s): | Freitas, J. Teixeira, A. Dias, J. Ferreira, A. Figueiredo, M. |
Editor: | Chng E.S. Li H. Meng H. Ma B. Xie L. |
Date: | 2014 |
Title: | Enhancing multimodal silent speech interfaces with feature selection |
Book title/volume: | 15th Annual Conference of the International Speech Communication Association (INTERSPEECH 2014), Proceedings |
Pages: | 1169 - 1173 |
Reference: | Freitas, J., Ferreira, A., Figueiredo, M., Teixeira, A,, & Dias, M.(2014). Enhancing multimodal silent speech interfaces with feature selection. Em Chng E.S., Li H., Meng H., Ma B., Xie L. (Eds.), 15th Annual Conference of the International Speech Communication Association (INTERSPEECH 2014), Proceedings (pp.1169 - 1173). Speech and Communication Association. http://hdl.handle.net/10071/25831 |
ISSN: | 2308-457X |
Keywords: | Multimodal Silent speech interfaces Supervised classification Feature extraction |
Abstract: | 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 |
Peerreviewed: | yes |
Access type: | Open Access |
Appears in Collections: | ISTAR-CRI - Comunicações a conferências internacionais |
Files in This Item:
File | Size | Format | |
---|---|---|---|
conferenceobject_22958.pdf | 185,81 kB | Adobe PDF | View/Open |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.