Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

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

A Novel Machine Learning Approach for Predicting Prognosis of SFTS Patients in the Early Stages of Disease.

The Canadian journal of infectious diseases & medical microbiology = Journal canadien des maladies infectieuses et de la microbiologie medicale·2026

Same author

Distinct Longitudinal Trajectories of SLEDAI-2K Scores Predict Prognosis in Systemic Lupus Erythematosus Based on Group-Based Trajectory Modeling.

Journal of immunology research·2026

Same author

T Follicular Helper Cell Immune Signatures Associated With Disease Severity in Severe Fever With Thrombocytopenia Syndrome.

Journal of immunology research·2026

Same author

Integration of SFTSV Viral Load, Age, and Double-Negative B-Cells as Prognostic Biomarkers for Severe Fever With Thrombocytopenia Syndrome Outcomes.

Journal of immunology research·2026

Same author

Rare ANA patterns and their clinical correlates: a retrospective large-cohort study.

Clinical chemistry and laboratory medicine·2026

Same author

Longitudinal, Multi-Cycle Evaluation of Passive Function Improvement in People with Arm Spasticity Treated with Botulinum Toxin A.

Toxins·2026

Same journal

Logic, inference, understanding: cross-domain generalization for generative language models.

Frontiers in artificial intelligence·2026

Same journal

Label tree semantic losses for rich multi-class medical image segmentation.

Frontiers in artificial intelligence·2026

Same journal

Score-based generative diffusion models to synthesize full-dose FDG brain PET from MRI in epilepsy patients.

Frontiers in artificial intelligence·2026

Same journal

Resource-efficient retrieval-augmented question answering for the Indian Lok Sabha dataset.

Frontiers in artificial intelligence·2026

Same journal

Violation detection in power operation sites based on multi-scale detection and few-shot learning.

Frontiers in artificial intelligence·2026

Same journal

Deep reinforcement learning-based reversible medical image encryption framework for secure IoMT environments.

Frontiers in artificial intelligence·2026

See all related articles

Search research articles

Related Experiment Video

Updated: May 7, 2025

Computer-based Multitaper Spectrogram Program for Electroencephalographic Data

Computer-based Multitaper Spectrogram Program for Electroencephalographic Data

Published on: November 13, 2019

Interpreting CNN models for musical instrument recognition using multi-spectrogram heatmap analysis: a preliminary

Rujia Chen¹, Akbar Ghobakhlou¹, Ajit Narayanan¹

¹Computer Science and Software Engineering Department, Auckland University of Technology, Auckland, New Zealand.

Frontiers in Artificial Intelligence

|January 2, 2025

Summary

This summary is machine-generated.

This study evaluated spectrograms for musical instrument recognition using convolutional neural networks (CNNs). Mel-frequency cepstral coefficients (MFCC) and Log-Mel spectrograms proved most effective for classifying ten instruments.

Keywords:

convolutional neural networks feature extraction feature maps heatmaps music information retrieval musical instrument recognition pattern recognition spectrogram analysis

More Related Videos

Author Spotlight: Advancing Large-Scale Neural Dynamics Through HD-MEA Technology

Author Spotlight: Advancing Large-Scale Neural Dynamics Through HD-MEA Technology

Published on: March 8, 2024

Real-Time Proxy-Control of Re-Parameterized Peripheral Signals using a Close-Loop Interface

Real-Time Proxy-Control of Re-Parameterized Peripheral Signals using a Close-Loop Interface

Published on: May 8, 2021

Related Experiment Videos

Last Updated: May 7, 2025

Computer-based Multitaper Spectrogram Program for Electroencephalographic Data

Computer-based Multitaper Spectrogram Program for Electroencephalographic Data

Published on: November 13, 2019

Author Spotlight: Advancing Large-Scale Neural Dynamics Through HD-MEA Technology

Author Spotlight: Advancing Large-Scale Neural Dynamics Through HD-MEA Technology

Published on: March 8, 2024

Real-Time Proxy-Control of Re-Parameterized Peripheral Signals using a Close-Loop Interface

Real-Time Proxy-Control of Re-Parameterized Peripheral Signals using a Close-Loop Interface

Published on: May 8, 2021

Area of Science:

Music Information Retrieval (MIR)
Machine Learning
Audio Signal Processing

Background:

Musical instrument recognition is vital for MIR but challenging due to signal complexity.
Convolutional Neural Networks (CNNs) are increasingly used for audio classification tasks.

Purpose of the Study:

To compare the effectiveness of various spectrogram representations for musical instrument recognition.
To assess feature importance and model interpretability using statistical and visual analyses.

Main Methods:

Utilized CNNs to classify ten musical instruments from the NSynth database.
Analyzed Short-Time Fourier Transform (STFT), Log-Mel, MFCC, Chroma, Spectral Contrast, and Tonnetz spectrograms.
Employed visual heatmap analysis and statistical metrics (Difference Mean, KL Divergence, JS Divergence, Earth Mover's Distance) for interpretability.

Main Results:

MFCC and Log-Mel spectrograms generally outperformed other representations in instrument classification.
Different spectrograms revealed unique strengths in capturing specific instrument characteristics.
Analysis provided insights into the discriminative power of each feature type.

Conclusions:

Spectrogram choice significantly impacts musical instrument recognition performance.
MFCC and Log-Mel spectrograms offer a robust approach for CNN-based instrument classification.
The study enhances understanding for optimizing MIR systems and improving model interpretability.