Music. Co-Creative. AI
We read ML papers about music, try to actually understand them, and document what we learn. Interactive demos, code, and a lot of questions along the way.
Reading Schedule
What we're currently reading
Interactive Notes
Notes from past sessions
Music Generation
From masked acoustic tokens to anticipatory symbolic infilling
An overview of two approaches to music generation: VampNet's masked acoustic token modeling for audio-domain generation, and the Anticipatory Music Transformer's interleaved infilling for symbolic MIDI.
Music Transcription
Dual-objective CNNs to transformers to 16K-parameter models
An overview of three papers that shaped the trajectory of automatic music transcription, covering Onsets and Frames, MT3, and the lightweight NMP (Basic Pitch) model, with interactive visualizations of the main ideas.
DDSP From Scratch
A minimal differentiable synthesizer in PyTorch (trying to understand the paper)
Building a differentiable digital signal processing synthesizer from scratch, with interactive visualizations and audio experiments from our reading group session on Engel et al. (2020).
What we read
ML papers about music: synthesis, transcription, generative models, anything with a loss function and an audio output. We work through one or two a week.
How we share
Each session gets interactive notes with visualizations and audio demos (and usually some PyTorch). The goal is real intuition, not just a summary of the abstract.
Who it's for
Researchers, engineers, musicians, students. Anyone who wants to actually dig into the papers rather than just hear about them. Show up, ask questions, bring coffee.
Want in, have a paper to suggest, or want to present one?
Join the Google Group