Pre-training Music Classification Models via Music Source Separation
Fuente:
arXiv
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2023
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866910419078086656 |
|---|---|
| author | Garoufis, Christos Zlatintsi, Athanasia Maragos, Petros |
| author_facet | Garoufis, Christos Zlatintsi, Athanasia Maragos, Petros |
| contents | In this paper, we study whether music source separation can be used as a pre-training strategy for music representation learning, targeted at music classification tasks. To this end, we first pre-train U-Net networks under various music source separation objectives, such as the isolation of vocal or instrumental sources from a musical piece; afterwards, we attach a classification network to the pre-trained U-Net and jointly finetune the whole network. The features learned by the separation network are also propagated to the tail network through a convolutional feature adaptation module. Experimental results in two widely used and publicly available datasets indicate that pre-training the U-Nets with a music source separation objective can improve performance compared to both training the whole network from scratch and using the tail network as a standalone in two music classification tasks, music auto-tagging and music genre classification. We also show that our proposed framework can be successfully integrated into both convolutional and Transformer-based backends, highlighting its modularity. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2310_15845 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | Pre-training Music Classification Models via Music Source Separation Garoufis, Christos Zlatintsi, Athanasia Maragos, Petros Audio and Speech Processing In this paper, we study whether music source separation can be used as a pre-training strategy for music representation learning, targeted at music classification tasks. To this end, we first pre-train U-Net networks under various music source separation objectives, such as the isolation of vocal or instrumental sources from a musical piece; afterwards, we attach a classification network to the pre-trained U-Net and jointly finetune the whole network. The features learned by the separation network are also propagated to the tail network through a convolutional feature adaptation module. Experimental results in two widely used and publicly available datasets indicate that pre-training the U-Nets with a music source separation objective can improve performance compared to both training the whole network from scratch and using the tail network as a standalone in two music classification tasks, music auto-tagging and music genre classification. We also show that our proposed framework can be successfully integrated into both convolutional and Transformer-based backends, highlighting its modularity. |
| title | Pre-training Music Classification Models via Music Source Separation |
| topic | Audio and Speech Processing |
| url | https://arxiv.org/abs/2310.15845 |