English

NONOTO: A Model-agnostic Web Interface for Interactive Music Composition by Inpainting

Human-Computer Interaction 2019-07-25 v1 Machine Learning Sound Audio and Speech Processing

Abstract

Inpainting-based generative modeling allows for stimulating human-machine interactions by letting users perform stylistically coherent local editions to an object using a statistical model. We present NONOTO, a new interface for interactive music generation based on inpainting models. It is aimed both at researchers, by offering a simple and flexible API allowing them to connect their own models with the interface, and at musicians by providing industry-standard features such as audio playback, real-time MIDI output and straightforward synchronization with DAWs using Ableton Link.

Keywords

Cite

@article{arxiv.1907.10380,
  title  = {NONOTO: A Model-agnostic Web Interface for Interactive Music Composition by Inpainting},
  author = {Théis Bazin and Gaëtan Hadjeres},
  journal= {arXiv preprint arXiv:1907.10380},
  year   = {2019}
}

Comments

3 pages, 1 figure. Published as a conference paper at the 10th International Conference on Computational Creativity (ICCC 2019), UNC Charlotte, North Carolina

R2 v1 2026-06-23T10:29:18.186Z