Spectrogram Inpainting for Interactive Generation of Instrument Sounds

TL;DR

This paper introduces a novel spectrogram inpainting method for instrument sound generation, combining VQ-VAE-2 and Transformers, enabling interactive sound shaping for musicians and artists.

Contribution

It adapts image inpainting techniques to spectrograms using VQ-VAE-2 and Transformers, and provides an open-source interactive tool for sound editing.

Findings

Effective spectrogram inpainting demonstrated on NSynth dataset

Open-source web interface enables interactive sound transformation

Method allows fine-grained control over instrument sound synthesis

Abstract

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.