Transfer learning for music classification and regression tasks

Keunwoo Choi, György Fazekas, Mark Sandler, Kyunghyun Cho

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

In this paper, we present a transfer learning approach for music classification and regression tasks. We propose to use a pre-trained convnet feature, a concatenated feature vector using the activations of feature maps of multiple layers in a trained convolutional network. We show how this convnet feature can serve as general-purpose music representation. In the experiments, a convnet is trained for music tagging and then transferred to other music-related classification and regression tasks. The convnet feature outperforms the baseline MFCC feature in all the considered tasks and several previous approaches that are aggregating MFCCs as well as low- and high-level music features.

Original languageEnglish (US)
Title of host publicationProceedings of the 18th International Society for Music Information Retrieval Conference, ISMIR 2017
EditorsSally Jo Cunningham, Zhiyao Duan, Xiao Hu, Douglas Turnbull
PublisherInternational Society for Music Information Retrieval
Pages141-149
Number of pages9
ISBN (Electronic)9789811151798
StatePublished - 2017
Event18th International Society for Music Information Retrieval Conference, ISMIR 2017 - Suzhou, China
Duration: Oct 23 2017Oct 27 2017

Publication series

NameProceedings of the 18th International Society for Music Information Retrieval Conference, ISMIR 2017

Conference

Conference18th International Society for Music Information Retrieval Conference, ISMIR 2017
Country/TerritoryChina
CitySuzhou
Period10/23/1710/27/17

ASJC Scopus subject areas

  • Music
  • Information Systems

Fingerprint

Dive into the research topics of 'Transfer learning for music classification and regression tasks'. Together they form a unique fingerprint.

Cite this