Nathan Pruyne

A massive thank you to my collaborators Ben Stoler, @chenwanch1, @cyhuang_tw, @shinjiw_at_cmu, and @chrisdonahuey, to Sony AI for funding, and to our data annotators at CMU!

Check out the links below to download MulTTiPop and for more information: 🎼Preview: gclef-cmu.org/multtipop 🤗Dataset: huggingface.co/datasets/gclef… 📃Paper: arxiv.org/abs/2607.08756

Introducing 🎼🫧MulTTiPop, an evaluation dataset of multitrack pop music for automatic music transcription! MulTTiPop contains 3.5 hours (572 segments) of aligned multitrack pop audio and MIDI, and can be previewed at gclef-cmu.org/multtipop 🧵1/7

Nathan Pruyne, Benjamin Stoler, William Chen, Chien-yu Huang, Shinji Watanabe, Chris Donahue, "MulTTiPop: A Multitrack Transcription Dataset for Pop Music" arxiv.org/abs/2607.08756

🎼 Can we turn music into readable code? Excited to share Decomposer, a post-training framework for symbolic music decompilation! Given MIDI, Decomposer recovers an executable program in Strudel that reconstructs the music while exposing patterns, harmony, rhythm, and voices as editable code. 🧵 [1/5]