Papers › Spectrogram Inpainting for Interactive Generation of Instrument Sounds

Spectrogram Inpainting for Interactive Generation of Instrument Sounds

15 Apr 2021arXiv:2104.07519archive 2025-07-28

Théis Bazin, Gaëtan Hadjeres, Philippe Esling, Mikhail Malt

Modern approaches to sound synthesis using deep neural networks are hard to control, especially when fine-grained conditioning information is not available, hindering their adoption by musicians. In this paper, we cast the generation of individual instrumental notes as an inpainting-based task, introducing novel and unique ways to iteratively shape sounds. To this end, we propose a two-step approach: first, we adapt the VQ-VAE-2 image generation architecture to spectrograms in order to convert real-valued spectrograms into compact discrete codemaps, we then implement token-masked Transformers for the inpainting-based generation of these codemaps. We apply the proposed architecture on the NSynth dataset on masked resampling tasks. Most crucially, we open-source an interactive web interface to transform sounds by inpainting, for artists and practitioners alike, opening up to new, creative uses.

PaperPDFCode

Code

SonyCSLParis/interactive-spectrogram-inpainting officialmentioned in paperpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Image Generation

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

PixelCNN

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections