 |
Communication dans un congrès
Electroencephalographic based brain computer interface for unspoken speech
Abstract : This paper presents a Brain Computer Interface methodology for unspoken speech recognition based on Electroencephalography (EEG). Each phase within this approach is presented and discussed, followed by the noise elimination methodology and ends up by features extraction and data classification. The presented work consists of database construction with features vectors that will be classified into different classes by applying an articial neural network with three layers. The proposed approach provides results with high percentage of recognition (93% Testing, 95% Validation) when applied on two English words ON/OFF acquired from 2 different resources.
Keywords :
unspoken speech recognition
speech recognition
Databases
electroencephalographic based brain computer interface
Electroencephalography
English words
feature extraction
features extraction
features vectors
neural nets
noise elimination methodology
signal classification
database construction
data classification
brain-computer interfaces
Brain Computer Interface methodology
Biological neural networks
articial neural network
https://hal.univ-angers.fr/hal-02527882
Contributeur : Okina Université d'Angers <>
Soumis le : mercredi 1 avril 2020 - 15:11:12
Dernière modification le : mercredi 1 avril 2020 - 20:19:40
Contributeur : Okina Université d'Angers <>
Soumis le : mercredi 1 avril 2020 - 15:11:12
Dernière modification le : mercredi 1 avril 2020 - 20:19:40
