Denoising diffusion models (DDMs) have led to staggering performance leaps in image
generation, editing and restoration. However, existing DDMs use very large datasets for …

Recent advances in visually-induced audio generation are based on sampling short, low-
fidelity, and one-class sounds. Moreover, sampling 1 second of audio from the state-of-the …

An ideal music synthesizer should be both interactive and expressive, generating high-
fidelity audio in realtime for arbitrary combinations of instruments and notes. Recent neural …

This paper presents CQT-Diff, a data-driven generative audio model that can, once trained,
be used for solving various different audio inverse problems in a problem-agnostic setting …

Deep learning in general focuses on training a neural network from large labeled datasets.
Yet, in many cases there is value in training a network just from the input at hand. This may …

Existing generative models for 3D shapes are typically trained on a large 3D dataset, often
of a specific object category. In this paper, we investigate the deep generative model that …

A vocoder is a conditional audio generation model that converts acoustic features such as
mel-spectrograms into waveforms. Taking inspiration from Differentiable Digital Signal …

Audio inpainting aims to reconstruct missing segments in corrupted recordings. Most of
existing methods produce plausible reconstructions when the gap lengths are short, but …

Controllable neural audio synthesis of sound effects is a challenging task due to the
potential scarcity and spectro-temporal variance of the data. Differentiable digital signal …

In this manuscript, we propose a novel method to perform audio inpainting, ie, the
restoration of audio signals presenting multiple missing parts. Audio inpainting can be …