Decoding imagined speech with delay differential analysis

Speech decoding from non-invasive EEG signals can achieve relatively high accuracy (70-80%) for strictly delimited classification tasks, but for more complex tasks non-invasive speech decoding typically yields a 20-50% classification accuracy. However, decoder generalization, or how well algorithms...

Full description

Saved in:
Bibliographic Details
Published inFrontiers in human neuroscience Vol. 18; p. 1398065
Main Authors Carvalho, Vinícius Rezende, Mendes, Eduardo Mazoni Andrade Marçal, Fallah, Aria, Sejnowski, Terrence J, Comstock, Lindy, Lainscsek, Claudia
Format Journal Article
LanguageEnglish
Published Switzerland Frontiers Research Foundation 17.05.2024
Frontiers Media S.A
Subjects
Accuracy
Business metrics
Classification
Datasets
Deep learning
delay differential analysis
EEG
Electroencephalography
non-linear dynamics
Performance evaluation
Receivers & amplifiers
Signal processing
Speech
speech decoding
electroencephalography
speech decoding
non-linear dynamics
delay differential analysis
signal processing
Online AccessGet full text

Cover

More Information
Summary:Speech decoding from non-invasive EEG signals can achieve relatively high accuracy (70-80%) for strictly delimited classification tasks, but for more complex tasks non-invasive speech decoding typically yields a 20-50% classification accuracy. However, decoder generalization, or how well algorithms perform objectively across datasets, is complicated by the small size and heterogeneity of existing EEG datasets. Furthermore, the limited availability of open access code hampers a comparison between methods. This study explores the application of a novel non-linear method for signal processing, delay differential analysis (DDA), to speech decoding. We provide a systematic evaluation of its performance on two public imagined speech decoding datasets relative to all publicly available deep learning methods. The results support DDA as a compelling alternative or complementary approach to deep learning methods for speech decoding. DDA is a fast and efficient time-domain open-source method that fits data using only few strong features and does not require extensive preprocessing.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 23
ISSN:1662-5161
1662-5161
DOI:10.3389/fnhum.2024.1398065