Sample-level CNN Architectures for Music Auto-tagging Using Raw Waveforms

Taejun Kim, Jongpil Lee, Juhan Nam
10/28/2017
cs.SDcs.LGcs.MM

Official code: tae-jun/resemul (58 stars, TensorFlow, last commit 2018-04-13).

Abstract

Recent work has shown that the end-to-end approach using convolutional neural network (CNN) is effective in various types of machine learning tasks. For audio signals, the approach takes raw waveforms as input using an 1-D convolution layer. In this paper, we improve the 1-D CNN architecture for music auto-tagging by adopting building blocks from state-of-the-art image classification models, ResNets and SENets, and adding multi-level feature aggregation to it. We compare different combinations of the modules in building CNN architectures. The results show that they achieve significant improvements over previous state-of-the-art models on the MagnaTagATune dataset and comparable results on Million Song Dataset. Furthermore, we analyze and visualize our model to show how the 1-D CNN operates.

View on arXivView PDF

Code Implementations(1)

tae-jun/resemulOfficial100%
TensorFlow

A TensorFlow+Keras implementation of "Sample-level CNN Architectures for Music Auto-tagging Using Raw Waveforms"

5813Python, Jupyter NotebookOct 19, 20178 years ago
deep-learningkerasmusic-classificationtensorflow

Similar Papers

Evaluation of CNN-based Automatic Music Tagging Models

88% match1 repo4402020

Convolutional Recurrent Neural Networks for Music Classification

87% match1 repo132016

General audio tagging with ensembling convolutional neural network and statistical features

87% match1 repo782018

musicnn: Pre-trained convolutional neural networks for music audio tagging

86% match3 repos7242019

Convolutional Gated Recurrent Neural Network Incorporating Spatial Features for Audio Tagging

84% match2017

Unsupervised Feature Learning Based on Deep Models for Environmental Audio Tagging

84% match2016

Cite this paper

@article{kim2017samplelevel,
  title  = {Sample-level CNN Architectures for Music Auto-tagging Using Raw Waveforms},
  author = {Taejun Kim and Jongpil Lee and Juhan Nam},
  year   = {2017},
  eprint = {1710.10451},
  archivePrefix = {arXiv},
  url    = {https://arxiv.org/abs/1710.10451}
}

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/1710.10451.svg)](https://codeofpaper.com/paper/1710.10451)

Discussion