Multimodal Metric Learning for Tag-Based Music Retrieval
Authors:
- 6 June 2021
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 591-595
Abstract
Tag-based music retrieval is crucial to browse large-scale mu-sic 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, met-ric 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.Keywords
All Related Versions
Funding Information
- Ministry of Economy
This publication has 9 references indexed in Scilit:
- Multimodal Deep Learning for Music Genre ClassificationTransactions of the International Society for Music Information Retrieval, 2018
- Learning Deep Structure-Preserving Image-Text Embeddings2016
- Discriminative Learning of Deep Convolutional Feature Point Descriptors2015
- Deep Metric Learning Using Triplet Network2015
- FaceNet: A unified embedding for face recognition and clustering2015
- Glove: Global Vectors for Word Representation2014
- The million song dataset challenge2012
- Collaborative Filtering for Implicit Feedback Datasets2008
- Explaining collaborative filtering recommendations2000