PhD in AI & Audio/Music @QMUL with @SpotifyResearch Deep Generative Models / Disentangled Representation Learning / Unsupervised Learning / Controllable Audio Generation Intern @StabilityAI / Prev. Intern @SonyAI @AIST_JP https://yjlolo.github.iohttps://bsky.app/profile/jun-luolo.bsky.socialhttps://bsky.app/profile/jun-luolo.bsky.social/post/3ldclkr34e222How to train a model to extract separate entities of representation associated to individual sources of a music mixture? How to also divide each entity into subspaces of pitch and timbre? How to then have the model take arbitrary combinations of these building blocks to sample novel mixtures?15 Dec 2024 00:45 +0000at://did:plc:bzsbz2i6bpkrf2fmkdaa3stq/app.bsky.feed.post/3ldclkr34e222