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

Abstract

Pronounced as "musician", the musicnn library contains a set of pre-trained musically motivated convolutional neural networks for music audio tagging: https://github.com/jordipons/musicnn. This repository also includes some pre-trained vgg-like baselines. These models can be used as out-of-the-box music audio taggers, as music feature extractors, or as pre-trained models for transfer learning. We also provide the code to train the aforementioned models: https://github.com/jordipons/musicnn-training. This framework also allows implementing novel models. For example, a musically motivated convolutional neural network with an attention-based output layer (instead of the temporal pooling layer) can achieve state-of-the-art results for music audio tagging: 90.77 ROC-AUC / 38.61 PR-AUC on the MagnaTagATune dataset --- and 88.81 ROC-AUC / 31.51 PR-AUC on the Million Song Dataset.

Accepted to be presented at the Late-Breaking/Demo session of ISMIR 2019

Cited by in corpus (8)

• PANNs: Large-Scale Pretrained Audio Neural Networks for Audio Pattern Recognition
• Acoustic Anomaly Detection for Machine Sounds based on Image Transfer Learning
• Enriched Music Representations with Multiple Cross-modal Contrastive Learning
• Exploiting Negative Preference in Content-based Music Recommendation with Contrastive Learning
• Learning Music Sequence Representation from Text Supervision
• Mood Classification Using Listening Data
• Comparative Analysis of Pretrained Audio Representations in Music Recommender Systems
• Visual Attention for Musical Instrument Recognition