Yin-Jyun (Jun) Luo's Avatar

Yin-Jyun (Jun) Luo

@jun-luolo.bsky.social

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.io

133 Followers  |  230 Following  |  2 Posts  |  Joined: 20.11.2024  |  1.5131

Latest posts by jun-luolo.bsky.social on Bluesky

At the NeurIPS workshop of Audio Imagination, we present a supervised method as a preliminary step towards answering these questions.
openreview.net/pdf?id=Zhc6Z...

15.12.2024 00:45 β€” πŸ‘ 2    πŸ” 0    πŸ’¬ 0    πŸ“Œ 0

How 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?

15.12.2024 00:45 β€” πŸ‘ 3    πŸ” 0    πŸ’¬ 1    πŸ“Œ 0

@jun-luolo is following 20 prominent accounts