Decoding speech information from EEG data with 4-, 7- and 11-month-old infants: Using convolutional neural network, mutual information-based and backward linear models.

EEG backward linear model convolutional neural network infant mutual information speech decoding

Journal

Journal of neuroscience methods
ISSN: 1872-678X
Titre abrégé: J Neurosci Methods
Pays: Netherlands
ID NLM: 7905558

Informations de publication

Date de publication:
19 Dec 2023
Historique:
received: 18 04 2023
revised: 11 12 2023
accepted: 15 12 2023
medline: 22 12 2023
pubmed: 22 12 2023
entrez: 21 12 2023
Statut: aheadofprint

Résumé

Computational models that successfully decode neural activity into speech are increasing in the adult literature, with convolutional neural networks (CNNs), backward linear models, and mutual information (MI) models all being applied to neural data in relation to speech input. This is not the case in the infant literature. Three different computational models, two novel for infants, were applied to decode low-frequency speech envelope information. Previously-employed backward linear models were compared to novel CNN and MI-based models. Fifty infants provided EEG recordings when aged 4, 7, and 11 months, while listening passively to natural speech (sung or chanted nursery rhymes) presented by video with a female singer. Each model computed speech information for these nursery rhymes in two different low-frequency bands, delta and theta, thought to provide different types of linguistic information. All three models demonstrated significant levels of performance for delta-band neural activity from 4 months of age, with two of three models also showing significant performance for theta-band activity. All models also demonstrated higher accuracy for the delta-band neural responses. None of the models showed developmental (age-related) effects. The data demonstrate that the choice of algorithm used to decode speech envelope information from neural activity in the infant brain determines the developmental conclusions that can be drawn. The modelling shows that better understanding of the strengths and weaknesses of each modelling approach is fundamental to improving our understanding of how the human brain builds a language system.

Sections du résumé

BACKGROUND BACKGROUND
Computational models that successfully decode neural activity into speech are increasing in the adult literature, with convolutional neural networks (CNNs), backward linear models, and mutual information (MI) models all being applied to neural data in relation to speech input. This is not the case in the infant literature.
NEW METHOD METHODS
Three different computational models, two novel for infants, were applied to decode low-frequency speech envelope information. Previously-employed backward linear models were compared to novel CNN and MI-based models. Fifty infants provided EEG recordings when aged 4, 7, and 11 months, while listening passively to natural speech (sung or chanted nursery rhymes) presented by video with a female singer.
RESULTS RESULTS
Each model computed speech information for these nursery rhymes in two different low-frequency bands, delta and theta, thought to provide different types of linguistic information. All three models demonstrated significant levels of performance for delta-band neural activity from 4 months of age, with two of three models also showing significant performance for theta-band activity. All models also demonstrated higher accuracy for the delta-band neural responses. None of the models showed developmental (age-related) effects.
COMPARISONS WITH EXISTING METHODS METHODS
The data demonstrate that the choice of algorithm used to decode speech envelope information from neural activity in the infant brain determines the developmental conclusions that can be drawn.
CONCLUSIONS CONCLUSIONS
The modelling shows that better understanding of the strengths and weaknesses of each modelling approach is fundamental to improving our understanding of how the human brain builds a language system.

Identifiants

pubmed: 38128783
pii: S0165-0270(23)00255-8
doi: 10.1016/j.jneumeth.2023.110036
pii:
doi:

Types de publication

Journal Article

Langues

eng

Sous-ensembles de citation

IM

Pagination

110036

Informations de copyright

Copyright © 2023 The Authors. Published by Elsevier B.V. All rights reserved.

Déclaration de conflit d'intérêts

Declaration of Competing Interest The authors declare no competing financial interests.

Auteurs

Mahmoud Keshavarzi (M)

Centre for Neuroscience in Education, Department of Psychology, University of Cambridge, Downing Street, Cambridge, CB2 3EB, UK. Electronic address: mk919@cam.ac.uk.

Áine Ní Choisdealbha (ÁN)

Centre for Neuroscience in Education, Department of Psychology, University of Cambridge, Downing Street, Cambridge, CB2 3EB, UK.

Adam Attaheri (A)

Centre for Neuroscience in Education, Department of Psychology, University of Cambridge, Downing Street, Cambridge, CB2 3EB, UK.

Sinead Rocha (S)

Centre for Neuroscience in Education, Department of Psychology, University of Cambridge, Downing Street, Cambridge, CB2 3EB, UK.

Perrine Brusini (P)

Centre for Neuroscience in Education, Department of Psychology, University of Cambridge, Downing Street, Cambridge, CB2 3EB, UK.

Samuel Gibbon (S)

Centre for Neuroscience in Education, Department of Psychology, University of Cambridge, Downing Street, Cambridge, CB2 3EB, UK.

Panagiotis Boutris (P)

Centre for Neuroscience in Education, Department of Psychology, University of Cambridge, Downing Street, Cambridge, CB2 3EB, UK.

Natasha Mead (N)

Centre for Neuroscience in Education, Department of Psychology, University of Cambridge, Downing Street, Cambridge, CB2 3EB, UK.

Helen Olawole-Scott (H)

Centre for Neuroscience in Education, Department of Psychology, University of Cambridge, Downing Street, Cambridge, CB2 3EB, UK.

Henna Ahmed (H)

Centre for Neuroscience in Education, Department of Psychology, University of Cambridge, Downing Street, Cambridge, CB2 3EB, UK.

Sheila Flanagan (S)

Centre for Neuroscience in Education, Department of Psychology, University of Cambridge, Downing Street, Cambridge, CB2 3EB, UK.

Kanad Mandke (K)

Centre for Neuroscience in Education, Department of Psychology, University of Cambridge, Downing Street, Cambridge, CB2 3EB, UK.

Usha Goswami (U)

Centre for Neuroscience in Education, Department of Psychology, University of Cambridge, Downing Street, Cambridge, CB2 3EB, UK.

Classifications MeSH