Abstract | ||
---|---|---|
Tag-based music retrieval is crucial to browse large-scale music libraries efficiently. Hence, automatic music tagging has been actively explored, mostly as a classification task, which has an inherent limitation: a fixed vocabulary. On the other hand, metric learning enables flexible vocabularies by using pretrained word embeddings as side information. Also, metric learning has proven its suitability for cross-modal retrieval tasks in other domains (e.g., text-to-image) by jointly learning a multimodal embedding space. 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. Our experimental results show that the proposed ideas enhance the retrieval system quantitatively and qualitatively. Furthermore, we release the MSD500: a subset of the Million Song Dataset (MSD) containing 500 cleaned tags, 7 manually annotated tag categories, and user taste profiles. |
Year | DOI | Venue |
---|---|---|
2021 | 10.1109/ICASSP39728.2021.9413514 | 2021 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP 2021) |
Keywords | DocType | Citations |
Metric learning, Music retrieval, Multi-modality, Auto-tagging | Conference | 0 |
PageRank | References | Authors |
0.34 | 0 | 5 |
Name | Order | Citations | PageRank |
---|---|---|---|
Minz Won | 1 | 3 | 3.18 |
Sergio Oramas | 2 | 17 | 2.65 |
Oriol Nieto | 3 | 89 | 10.40 |
Fabien Gouyon | 4 | 103 | 8.54 |
Xavier Serra | 5 | 1014 | 118.93 |