Convolutional Neural Network Achieves Human-level Accuracy in Music Genre Classification

Mingwen Dong
2/27/2018
cs.SDcs.LGeess.AS

Official code: ds7711/music_genre_classification (14 stars, last commit 2017-05-14).

Abstract

Music genre classification is one example of content-based analysis of music signals. Traditionally, human-engineered features were used to automatize this task and 61% accuracy has been achieved in the 10-genre classification. However, it's still below the 70% accuracy that humans could achieve in the same task. Here, we propose a new method that combines knowledge of human perception study in music genre classification and the neurophysiology of the auditory system. The method works by training a simple convolutional neural network (CNN) to classify a short segment of the music signal. Then, the genre of a music is determined by splitting it into short segments and then combining CNN's predictions from all short segments. After training, this method achieves human-level (70%) accuracy and the filters learned in the CNN resemble the spectrotemporal receptive field (STRF) in the auditory system.

View on arXivView PDF

Code Implementations(1)

ds7711/music_genre_classificationOfficial100%

CNN achieves human-level accuracy in music genre classification

141Python, Jupyter NotebookMay 13, 20179 years ago

Similar Papers

Music Genre Classification: Training an AI model

89% match2024

GAFX: A General Audio Feature eXtractor

86% match2022

Attention-guided Spectrogram Sequence Modeling with CNNs for Music Genre Classification

86% match1 repo2024

Music Genre Classification: A Comparative Analysis of Classical Machine Learning and Deep Learning Approaches

86% match2026

Music Genre Classification: A Comparative Analysis of CNN and XGBoost Approaches with Mel-frequency cepstral coefficients and Mel Spectrograms

86% match2024

Music Genre Classification using Large Language Models

85% match2024

Cite this paper

@article{dong2018convolutional,
  title  = {Convolutional Neural Network Achieves Human-level Accuracy in Music Genre Classification},
  author = {Mingwen Dong},
  year   = {2018},
  eprint = {1802.09697},
  archivePrefix = {arXiv},
  url    = {https://arxiv.org/abs/1802.09697}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/1802.09697.svg)](https://codeofpaper.com/paper/1802.09697)

Discussion