Evaluation of CNN-based Automatic Music Tagging Models
By Minz Won, Andrés Ferraro, Dmitry Bogdanov, Xavier Serra. 2020
113 citations recorded by the source corpus.
Recent advances in deep learning accelerated the development of content-based automatic music tagging systems. Music information retrieval (MIR) researchers proposed various architecture designs, mainly based on convolutional neural networks (CNNs), that achieve state-of-the-art results in this multi-label binary classification task. However, due to the differences in experimental setups followed by researchers, such as using different dataset splits and software versions for evaluation, it is difficult to compare the proposed architectures directly with each other. To facilitate further research, in this paper we conduct a consistent evaluation of different music tagging models on three datasets (MagnaTagATune, Million Song Dataset, and MTG-Jamendo) and provide reference results using common evaluation metrics (ROC-AUC and PR-AUC). Furthermore, all the models are evaluated with perturbed inputs to investigate the generalization capabilities concerning time stretch, pitch shift, dynamic range compression, and addition of white noise. For reproducibility, we provide the PyTorch implementations with the pre-trained models.
Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Signal Processing
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
In Computer Vision and Pattern Recognition
In Signal Processing
- Eduardo Fonseca
- Xavier Serra
- Andrés Ferraro
- Frederic Font
- Xavier Favory
- Jordi Pons
- D. Ellis
- Manoj Plakal
Citations in the corpus
- FSD50K: An Open Dataset of Human-Labeled Sound Events (2020, neutral): “This result accords with similar recent findings in music genre recognition [124].”
- Improving Sound Event Classification by Increasing Shift Invariance in Convolutional Neural Networks (2021, result): “This type of architecture has been widely used for SET [2, 22, 23, 24] and is the most competitive baseline for FSD50K when compared to others of higher complexity [16]—which also accords with recent music tagging evaluations [25].”