Audio-signal music recommendation that generates playlists from extracted analysis data is now available without licensing.
The system takes a user’s chosen track, extracts audio signal analysis features from it, and then selects additional songs that match those features to form a playlist. Its technical edge is feature-based retrieval—turning raw audio into a reusable “analysis data” representation rather than relying only on user history. Previously, deploying a similar playlist-generation workflow could require paying for or licensing the patented recommendation method.
Build on-device or web music playlist generators using extracted audio features, without ongoing recommendation-method royalties.
A music recommendation system receives a user selection of desired music, retrieves analysis data associated with the selected music, and generates a playlist of songs based on the analysis data. The analysis data is generated based on a processing of one or more audio signals associated with the selected music.
Post a problem you're solving with this technology and connect with founders, investors, and researchers.