Music theme recognition using CNN and self-attention
Sound
2019-11-19 v1 Machine Learning
Audio and Speech Processing
Abstract
We present an efficient architecture to detect mood/themes in music tracks on autotagging-moodtheme subset of the MTG-Jamendo dataset. Our approach consists of two blocks, a CNN block based on MobileNetV2 architecture and a self-attention block from Transformer architecture to capture long term temporal characteristics. We show that our proposed model produces a significant improvement over the baseline model. Our model (team name: AMLAG) achieves 4th place on PR-AUC-macro Leaderboard in MediaEval 2019: Emotion and Theme Recognition in Music Using Jamendo.
Cite
@article{arxiv.1911.07041,
title = {Music theme recognition using CNN and self-attention},
author = {Manoj Sukhavasi and Sainath Adapa},
journal= {arXiv preprint arXiv:1911.07041},
year = {2019}
}
Comments
MediaEval 2019, 27-29 October 2019, Sophia Antipolis, France