Machine learning accurately classifies neural responses to rhythmic speech vs. non-speech from 8-week-old infant EEG.

Journal: Brain and language
Published Date: Jun 7, 2021

Abstract

Currently there are no reliable means of identifying infants at-risk for later language disorders. Infant neural responses to rhythmic stimuli may offer a solution, as neural tracking of rhythm is atypical in children with developmental language disorders. However, infant brain recordings are noisy. As a first step to developing accurate neural biomarkers, we investigate whether infant brain responses to rhythmic stimuli can be classified reliably using EEG from 95 eight-week-old infants listening to natural stimuli (repeated syllables or drumbeats). Both Convolutional Neural Network (CNN) and Support Vector Machine (SVM) approaches were employed. Applied to one infant at a time, the CNN discriminated syllables from drumbeats with a mean AUC of 0.87, against two levels of noise. The SVM classified with AUC 0.95 and 0.86 respectively, showing reduced performance as noise increased. Our proof-of-concept modelling opens the way to the development of clinical biomarkers for language disorders related to rhythmic entrainment.

Authors

  • Samuel Gibbon
    Centre for Neuroscience in Education, Department of Psychology, University of Cambridge, UK. Electronic address: samuel.gibbon@gmail.com.
  • Adam Attaheri
    Centre for Neuroscience in Education, Department of Psychology, University of Cambridge, UK.
  • Áine Ní Choisdealbha
    Centre for Neuroscience in Education, Department of Psychology, University of Cambridge, UK.
  • Sinead Rocha
    Centre for Neuroscience in Education, Department of Psychology, University of Cambridge, UK.
  • Perrine Brusini
    Centre for Neuroscience in Education, Department of Psychology, University of Cambridge, UK.
  • Natasha Mead
    Centre for Neuroscience in Education, Department of Psychology, University of Cambridge, UK.
  • Panagiotis Boutris
    Centre for Neuroscience in Education, Department of Psychology, University of Cambridge, UK.
  • Helen Olawole-Scott
    Centre for Neuroscience in Education, Department of Psychology, University of Cambridge, UK.
  • Henna Ahmed
    Centre for Neuroscience in Education, Department of Psychology, University of Cambridge, UK.
  • Sheila Flanagan
    Centre for Neuroscience in Education, Department of Psychology, University of Cambridge, UK.
  • Kanad Mandke
    Centre for Neuroscience in Education, Department of Psychology, University of Cambridge, UK.
  • Mahmoud Keshavarzi
    1 Department of Psychology, University of Cambridge, Cambridge, UK.
  • Usha Goswami
    Centre for Neuroscience in Education, Department of Psychology, University of Cambridge, UK.

Keywords

External Resources

Popular Topics
Recent Journals