I build OTONAMI, a pitch platform that connects independent artists with music curators — playlist...
OTONAMI's matcher uses three design decisions: recall-based genres, no tempo, neutral missing data. Each choice solved production failures (22% BPM collapse, new-artist penalties), showing robustness comes from design asymmetry and decoupling, not algorithm complexity.
I build OTONAMI, a pitch platform that connects independent
artists with music curators — playlist editors, radio DJs, bloggers, label scouts.
At its core is a single number: how well does this track fit this curator?
The math behind that number is textbook. Cosine similarity, Jaccard, a weighted
sum — nothing you can't find in a first-year course. What actually took real,
Create custom music playlists with these AI tools
Before Music Publishers Invest in AI, They Need to Know What They’re Fixing (Guest Column)
How AI Attribution Could Finally Pay Musicians for Training Data
One-Third of Musicians Now Use AI for Inspiration on Tracks They Release, Study Finds (Exclusive)
Singing a New Tune: Computational Music — The Link - The Magazine of CMU's School of Computer Science
I'm Kai. Twenty+ years in game dev. Music was always my weakest link — I could listen, but I couldn't...
For two years, the AI music industry has measured itself on one axis: generation quality. Can a model produce a believable vocal,…
A methodology-first look at 1,085 matches, 41 competitions, and one number that keeps...
The music AI startup is battling record labels and angry artists as it upends how millions of people create songs. Now, some of…
Building TagMyBeat: An AI Producer Tag Generator and a Browser-Based BPM & Key Finder...
I Built Finito: A Production Tracker That Actually Gets Music Producers *I created this...
