The Concatenator: A Bayesian Approach To Real Time Concatenative Musaicing
Christopher Tralie, Ben Cantil

TL;DR
The paper introduces 'The Concatenator,' a real-time Bayesian audio mosaicing system that efficiently synthesizes target sounds by concatenating audio windows, enabling scalable, interactive musical applications.
Contribution
It presents a novel Bayesian particle filter approach for real-time concatenative synthesis that scales independently of corpus size, allowing for long audio collections and dynamic user control.
Findings
System achieves real-time performance with large audio corpora.
Allows user-controlled parameters for grain length, pitch, and transition speed.
Qualitative tests show potential for live musical expression.
Abstract
We present ``The Concatenator,'' a real time system for audio-guided concatenative synthesis. Similarly to Driedger et al.'s ``musaicing'' (or ``audio mosaicing'') technique, we concatenate a set number of windows within a corpus of audio to re-create the harmonic and percussive aspects of a target audio stream. Unlike Driedger's NMF-based technique, however, we instead use an explicitly Bayesian point of view, where corpus window indices are hidden states and the target audio stream is an observation. We use a particle filter to infer the best hidden corpus states in real-time. Our transition model includes a tunable parameter to control the time-continuity of corpus grains, and our observation model allows users to prioritize how quickly windows change to match the target. Because the computational complexity of the system is independent of the corpus size, our system scales to…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsBanana Cultivation and Research
MethodsSparse Evolutionary Training
