The Effects of Noisy Labels on Deep Convolutional Neural Networks for Music Tagging

Keunwoo Choi, György Fazekas, Kyunghyun Cho, Mark Sandler

Research output: Contribution to journalArticlepeer-review


Deep neural networks (DNNs) have been successfully applied to music classification including music tagging. However, there are several open questions regarding the training, evaluation, and analysis of DNNs. In this paper, we investigate specific aspects of neural networks, the effects of noisy labels, to deepen our understanding of their properties. We analyze and (re-)validate a large music tagging dataset to investigate the reliability of training and evaluation. Using a trained network, we compute label vector similarities, which are compared to groundtruth similarity. The results highlight several important aspects of music tagging and neural networks. We show that networks can be effective despite relatively large error rates in groundtruth datasets, while conjecturing that label noise can be the cause of varying tag-wise performance differences. Finally, the analysis of our trained network provides valuable insight into the relationships between music tags. These results highlight the benefit of using data-driven methods to address automatic music tagging.

Original languageEnglish (US)
Pages (from-to)139-149
Number of pages11
JournalIEEE Transactions on Emerging Topics in Computational Intelligence
Issue number2
StatePublished - Apr 2018


  • Music tagging
  • convolutional neural networks

ASJC Scopus subject areas

  • Computer Science Applications
  • Control and Optimization
  • Computational Mathematics
  • Artificial Intelligence


Dive into the research topics of 'The Effects of Noisy Labels on Deep Convolutional Neural Networks for Music Tagging'. Together they form a unique fingerprint.

Cite this