Transfer Learning of Artist Group Factors to Musical Genre Classification

Transfer Learning of Artist Group Factors to Musical Genre Classification

Kim, Jaehun (TU Delft Multimedia Computing)
Won, Minz (Pompeu Fabra University)
Serra, Xavier (Pompeu Fabra University)
Liem, C.C.S. (TU Delft Multimedia Computing)

2018

The automated recognition of music genres from audio information is a challenging problem, as genre labels are subjective and noisy. Artist labels are less subjective and less noisy, while certain artists may relate more strongly to certain genres. At the same time, at prediction time, it is not guaranteed that artist labels are available for a given audio segment. Therefore, in this work, we propose to apply the transfer learning framework, learning artist-related information which will be used at inference time for genre classification. We consider different types of artist-related information, expressed through artist group factors, which will allow for more efficient learning and stronger robustness to potential label noise. Furthermore, we investigate how to achieve the highest validation accuracy on the given FMA dataset, by experimenting with various kinds of transfer methods, including single-task transfer, multi-task transfer and finally multi-task learning.

music information retrieval
multi-task learning
transfer learning
neural network

http://resolver.tudelft.nl/uuid:a48bba52-d5d2-4f5d-a84f-cd8884fcc1e4

https://doi.org/10.1145/3184558.3191823

International World Wide Web Conferences Steering Committee, Republic and Canton of Geneva, Switzerland

978-1-4503-5640-4

WWW'18 Companion Proceedings of the The Web Conference 2018

WWW 2018, 2018-04-23 → 2018-04-27, Lyon, France

Institutional Repository

conference paper

© 2018 Jaehun Kim, Minz Won, Xavier Serra, C.C.S. Liem