UCSD-MUSAIC

Exciting invited talk today by Megan Wei from Brown University on her #ISMIR2024 work, 'Do Music Generation Models Encode Music Theory?'!

Their novel SynTheory dataset & probing framework reveals how models like Jukebox & MusicGen encode fundamental music concepts.

16.01.2025 05:30 — 👍 5    🔁 0    💬 0    📌 0

PDMX: A Large-Scale Public Domain MusicXML Dataset for Symbolic Music Processing The recent explosion of generative AI-Music systems has raised numerous concerns over data copyright, licensing music from musicians, and the conflict between open-source AI and large prestige compani...

Hyped that 3/3 papers w/the folks
@ucsd-musaic.bsky.social
are accepted at #ICASSP2025!

PDMX: Public Domain Symbolic Music arxiv.org/abs/2409.10831
CoLLAP: Long-Context CLAP (~5 min) arxiv.org/abs/2410.02271
FUTGA-MIR: long music understanding for MIR tasks (arxiv soon)

Next stop, India!🇮🇳

20.12.2024 23:04 — 👍 7    🔁 1    💬 0    📌 0

We just created a Bluesky starter pack featuring people and groups working at the intersection of AI and music, covering both symbolic and audio approaches. Let us know if you'd like to be added or removed!

go.bsky.app/PBvFCxa

28.11.2024 03:20 — 👍 14    🔁 3    💬 2    📌 0

We’ve just launched our official Bluesky account! We’ll be sharing exciting AI x Music projects from UCSD (PIs: Julian McAuley, Taylor Berg-Kirkpatrick, Shlomo Dubnov).

28.11.2024 03:06 — 👍 3    🔁 0    💬 0    📌 0

We'll appreciate being added!

27.11.2024 05:39 — 👍 2    🔁 0    💬 0    📌 0