Main » ISMIR » 2021 » Proceedings of the 22nd International Society for Music Information Retrieval Conference, ISMIR 2021, Online, November 7-12, 2021 »

Learning a cross-domain embedding space of vocal and mixed audio with a structure-preserving triplet loss

Keunhyoung Luke Kim, Jongpil Lee, Sangeun Kum, Juhan Nam