Speech Imagery

A Wearable Ultra-Low-Power System for EEG-Based Speech-Imagery Interfaces
First fully wearable EEG speech-imagery system delivering 13-class decoding on GAP9 at 25.93 mW with >21 hours autonomy.
Thorir Mar Ingolfsson, Victor Javier Kartsch, Luca Benini, Andrea Cossettini
IEEE Xplore
IEEE BioCAS 2024
Oral presentation of VowelNet and poster presentation of Train-on-Request at IEEE BioCAS 2024 in Xi’an.
17, Oct, 2024 Xi'an International Conference Center, Xi'an, China
Slides VowelNet oral slides Train-on-Request poster PDF VowelNet publication Train-on-Request publication
IEEE BioCAS 2024
VowelNet: Enhancing Communication with Wearable EEG-Based Vowel Imagery
Lightweight imagined-speech decoder that runs on GAP9 at 17 mW using only eight EEG channels.
Thorir Mar Ingolfsson, Victor Javier Kartsch Morinigo, Andrea Cossettini, Xiaying Wang, Luca Benini
PDF PDF (ETH Research Collection)