Music Tagging
16 papers with code • 1 benchmarks • 3 datasets
Benchmarks
These leaderboards are used to track progress in Music Tagging
| Trend | Dataset | Best Model | Paper | Code | Compare |
|---|---|---|---|---|---|
|
MagnaTagATune
EMOPIA
Most implemented papers
Convolutional Recurrent Neural Networks for Music Classification
We introduce a convolutional recurrent neural network (CRNN) for music tagging.
Automatic tagging using deep convolutional neural networks
keunwoochoi/music-auto_tagging-keras
•
•
We present a content-based automatic music tagging algorithm using fully convolutional neural networks (FCNs).
Transfer learning for music classification and regression tasks
In this paper, we present a transfer learning approach for music classification and regression tasks.
audioLIME: Listenable Explanations Using Source Separation
Deep neural networks (DNNs) are successfully applied in a wide variety of music information retrieval (MIR) tasks but their predictions are usually not interpretable.
A Comparison of Audio Signal Preprocessing Methods for Deep Neural Networks on Music Tagging
GorillaBus/urban-audio-classifier
•
•
In this paper, we empirically investigate the effect of audio preprocessing on music tagging with deep neural networks.
Multimodal Metric Learning for Tag-based Music Retrieval
minzwon/tag-based-music-retrieval
•
•
In this paper, we investigate three ideas to successfully introduce multimodal metric learning for tag-based music retrieval: elaborate triplet sampling, acoustic and cultural music information, and domain-specific word embeddings.
Melon Playlist Dataset: a public dataset for audio-based playlist generation and music tagging
We present Melon Playlist Dataset, a public dataset of mel-spectrograms for 649, 091tracks and 148, 826 associated playlists annotated by 30, 652 different tags.
A Modulation Front-End for Music Audio Tagging
Modulation filter bank representations that have been actively researched as a basis for timbre perception have the potential to facilitate the extraction of perceptually salient features.
Codified audio language modeling learns useful representations for music information retrieval
Relative to representations from conventional MIR models which are pre-trained on tagging, we find that using representations from Jukebox as input features yields 30% stronger performance on average across four MIR tasks: tagging, genre classification, emotion recognition, and key detection.
Unsupervised Source Separation By Steering Pretrained Music Models
ethman/tagbox
•
•
We showcase an unsupervised method that repurposes deep models trained for music generation and music tagging for audio source separation, without any retraining.
