A Silent Speech Decoding System from EEG and EMG with Heterogenous Electrode Configurations

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Inoue, Masakazu, Sato, Motoshige, Tomeoka, Kenichi, Nah, Nathania, Hatakeyama, Eri, Arulkumaran, Kai, Horiguchi, Ilya, Sasai, Shuntaro
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908409198018560
author Inoue, Masakazu
Sato, Motoshige
Tomeoka, Kenichi
Nah, Nathania
Hatakeyama, Eri
Arulkumaran, Kai
Horiguchi, Ilya
Sasai, Shuntaro
author_facet Inoue, Masakazu
Sato, Motoshige
Tomeoka, Kenichi
Nah, Nathania
Hatakeyama, Eri
Arulkumaran, Kai
Horiguchi, Ilya
Sasai, Shuntaro
contents Silent speech decoding, which performs unvocalized human speech recognition from electroencephalography/electromyography (EEG/EMG), increases accessibility for speech-impaired humans. However, data collection is difficult and performed using varying experimental setups, making it nontrivial to collect a large, homogeneous dataset. In this study we introduce neural networks that can handle EEG/EMG with heterogeneous electrode placements and show strong performance in silent speech decoding via multi-task training on large-scale EEG/EMG datasets. We achieve improved word classification accuracy in both healthy participants (95.3%), and a speech-impaired patient (54.5%), substantially outperforming models trained on single-subject data (70.1% and 13.2%). Moreover, our models also show gains in cross-language calibration performance. This increase in accuracy suggests the feasibility of developing practical silent speech decoding systems, particularly for speech-impaired patients.
format Preprint
id arxiv_https___arxiv_org_abs_2506_13835
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle A Silent Speech Decoding System from EEG and EMG with Heterogenous Electrode Configurations
Inoue, Masakazu
Sato, Motoshige
Tomeoka, Kenichi
Nah, Nathania
Hatakeyama, Eri
Arulkumaran, Kai
Horiguchi, Ilya
Sasai, Shuntaro
Quantitative Methods
Machine Learning
Neurons and Cognition
Silent speech decoding, which performs unvocalized human speech recognition from electroencephalography/electromyography (EEG/EMG), increases accessibility for speech-impaired humans. However, data collection is difficult and performed using varying experimental setups, making it nontrivial to collect a large, homogeneous dataset. In this study we introduce neural networks that can handle EEG/EMG with heterogeneous electrode placements and show strong performance in silent speech decoding via multi-task training on large-scale EEG/EMG datasets. We achieve improved word classification accuracy in both healthy participants (95.3%), and a speech-impaired patient (54.5%), substantially outperforming models trained on single-subject data (70.1% and 13.2%). Moreover, our models also show gains in cross-language calibration performance. This increase in accuracy suggests the feasibility of developing practical silent speech decoding systems, particularly for speech-impaired patients.
title A Silent Speech Decoding System from EEG and EMG with Heterogenous Electrode Configurations
topic Quantitative Methods
Machine Learning
Neurons and Cognition
url https://arxiv.org/abs/2506.13835