Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Video

Updated: May 22, 2026

Memorization-Based Training and Testing Paradigm for Robust Vocal Identity Recognition in Expressive Speech Using Event-Related Potentials Analysis
05:48

Memorization-Based Training and Testing Paradigm for Robust Vocal Identity Recognition in Expressive Speech Using Event-Related Potentials Analysis

Published on: August 9, 2024

Single-trial EEG-based classification reveals instrument-specific timbre perception via traditional machine learning

P Satkunarajah1, S D Power2, B R Zendel1

  • 1Population Health and Applied Health Sciences, Faculty of Medicine, Memorial University of Newfoundland, Canada.

Neuroimage
|May 20, 2026
PubMed
Summary

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Cloning and expression of an endocellulase gene from a novel streptomycete isolated from an East African soda lake.

Extremophiles : life under extreme conditions·2001
Same author

Characterization of two cold-sensitive mutants of the beta-galactosidase from Lactobacillus delbruckii subsp. bulgaricus.

The Journal of biological chemistry·1994
Same author

The catR gene encoding a catalase from Aspergillus niger: primary structure and elevated expression through increased gene copy number and use of a strong promoter.

Molecular microbiology·1993
Same author

Altering the proteolytic activity of subtilisin through protein engineering.

Annals of the New York Academy of Sciences·1992
Same author

The nuclear-coded subunits of yeast cytochrome c oxidase. The amino acid sequences of subunits VII and VIIa, structural similarities between the three smallest polypeptides of the holoenzyme, and implications for biogenesis.

The Journal of biological chemistry·1986
Same author

Secretion and autoproteolytic maturation of subtilisin.

Proceedings of the National Academy of Sciences of the United States of America·1986

This study shows traditional machine learning can identify musical instruments from brainwaves (EEG). This research could lead to hearing aids that adapt to what music you want to hear.

Area of Science:

  • Neuroscience
  • Machine Learning
  • Bioacoustics

Background:

  • Hearing aid users often struggle with music perception.
  • Future hearing aids may adapt to user intent by monitoring brain activity.
  • Selective amplification of desired musical instruments is a potential application.

Purpose of the Study:

  • To assess if traditional machine learning can identify musical instruments from single-trial electroencephalography (EEG).
  • To explore the efficacy of various classifiers and feature sets for EEG-based musical instrument identification.

Main Methods:

  • Recorded EEG from 73 electrodes while participants listened to tones (Trombone, Clarinet, Cello, Piano, Pure Tone).
  • Investigated Linear Discriminant Analysis (LDA), Gradient Boosting (GB), Support Vector Machine (SVM), and k-NN classifiers.
Keywords:
auditoryeegmachine learningmusic cognitiontimbre perception

Related Experiment Videos

Last Updated: May 22, 2026

Memorization-Based Training and Testing Paradigm for Robust Vocal Identity Recognition in Expressive Speech Using Event-Related Potentials Analysis
05:48

Memorization-Based Training and Testing Paradigm for Robust Vocal Identity Recognition in Expressive Speech Using Event-Related Potentials Analysis

Published on: August 9, 2024

  • Utilized raw EEG, event-related potential (ERP)-based, harmonics-based, and regularity-based features.
  • Analyzed N1 and P2 ERP components for instrument-specific differences.

    • Main Results:

    • All four classifiers performed significantly above chance (20%) using raw EEG features (LDA: 34%, GB: 35%, SVM: 33%, k-NN: 26%).
    • Precision, Recall, and F1-scores correlated with overall accuracy.
    • Cello produced the largest P2 amplitude and earliest N1 latency; Pure Tone had the smallest P2 amplitude; Clarinet had the latest N1 latency.

    Conclusions:

    • Traditional machine learning methods show potential for identifying musical instruments from EEG data.
    • Further improvements may be achieved with advanced algorithms or feature transformations.
    • Distinct ERP characteristics (N1 latency, P2 amplitude) vary across different musical instruments and pure tones.