AI DJ plans and checks pop music mixes for better transitions
DJustify: Reason-and-Verify DJ Planning for Pop Transitions and Story-Driven Sets
Sound
Summary
Mixing vocal-rich popular music is difficult because deciding the next song, where to start it, and how to mix it all go together. The authors created DJustify, an AI DJ that uses a large language model to think through and suggest different mixing plans, then checks the audio quality to fix any mistakes. In tests, their system made better transitions than common methods and could arrange songs to tell an emotional story just like a human DJ. The checking part mainly catches rare but noticeable errors, while the planning part tries many options to find good mixes.
What this means in practice
- •For music streaming platforms: Automatically create smooth, story-driven playlists for pop music users with AI-chosen transitions and cue points.$Commercial implications: This system enables streaming platforms to offer enhanced automated DJ features that improve user listening experiences with pop music.
- •For live event audio teams: Assist DJs at live events by suggesting reliable transition plans and verifying audio quality for pop music mixes.
Authors
Wei-Han Hsu, Li-Jie Lin, Po-Hsuan Lai, Po-Hsiang Huang, Jeng-Yue Liu, Li Su, Yi-Hsuan Yang
Abstract
Automatic DJ systems mostly target electronic dance music, whose regular structure makes rule-based mixing relatively easier. Vocal-rich popular music is harder: which track to play next, where to cue it, and which transition to use are tied together, so fixed rules handle them poorly. We present DJustify, a pop AI-DJ that puts an LLM in a reason--propose--verify--repair loop and lets it choose the next track, cue points, and mixing technique together. The LLM samples several transition plans; an external acoustic checker then scores the rendered audio and triggers repair when a check fails. Sampling keeps several candidate transitions per track pair instead of one fixed mix. In blind listening tests our transitions beat Mosaikbox, a reimplemented crossfade, and a cue baseline that reuses the crossfade's cues; that last comparison shows most of the margin comes from cue placement. The same planner also picks and orders a set along an emotion arc: this improves story coherence over a no-story ablation, and within a set story and transition ratings show no measurable gap from a human DJ. The checker mainly adds reliability, not higher average quality: it repairs rare but audible errors such as cut vocals, while the planner stays non-deterministic.