Pattern learning with deep neural networks in EMG-based speech recognition

Author

Wand, Michael ; Schultz, Tanja

Author_Institution

Ist. Dalle Molle di Studi sull´Intell. Artificiale, Univ. of Lugano & SUPSI, Lugano, Switzerland

fYear

2014

fDate

26-30 Aug. 2014

Firstpage

4200

Lastpage

4203

Abstract

We report on classification of phones and phonetic features from facial electromyographic (EMG) data, within the context of our EMG-based Silent Speech interface. In this paper we show that a Deep Neural Network can be used to perform this classification task, yielding a significant improvement over conventional Gaussian Mixture models. Our central contribution is the visualization of patterns which are learned by the neural network. With increasing network depth, these patterns represent more and more intricate electromyographic activity.

Keywords

Gaussian processes; electromyography; feature extraction; learning (artificial intelligence); medical signal processing; mixture models; neural nets; neurophysiology; signal classification; speech processing; speech recognition; EMG-based silent speech interface; EMG-based speech recognition; Gaussian mixture models; deep neural networks; facial electromyographic data; pattern learning; phone feature classification; phonetic feature classification; Accuracy; Electromyography; Feature extraction; Neural networks; Speech; Speech recognition; Training;

fLanguage

English

Publisher

ieee

Conference_Titel

Engineering in Medicine and Biology Society (EMBC), 2014 36th Annual International Conference of the IEEE

Conference_Location

Chicago, IL

ISSN

1557-170X

Type

conf

DOI

10.1109/EMBC.2014.6944550

Filename

6944550