Contrastive Learning of Musical Representations

Autor: Spijkervet, J., Burgoyne, J.A., Lee, J.H., Lerch, A., Duan, Z., Nam, J., Rao, P., Van Kranenburg, P., Srinivasamurthy, A.

Publikováno v: Proceedings: The 22nd International Society for Music Information Retrieval Conference: ISMIR 2021 : November 7-12, 2021 (online), 673-681
STARTPAGE=673;ENDPAGE=681;TITLE=Proceedings: The 22nd International Society for Music Information Retrieval Conference

While deep learning has enabled great advances in many areas of music, labeled music datasets remain especially hard, expensive, and time-consuming to create. In this work, we introduce SimCLR to the music domain and contribute a large chain of audio

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::bef723bcf82eec5c3b95093c83a7da68
https://doi.org/10.5281/zenodo.5624573