research
∙
09/13/2023
VRDMG: Vocal Restoration via Diffusion Posterior Sampling with Multiple Guidance
Restoring degraded music signals is essential to enhance audio quality f...
share
research
∙
08/14/2023
The Sound Demixing Challenge 2023 x2013 Music Demixing Track
This paper summarizes the music demixing (MDX) track of the Sound Demixi...
research
∙
06/01/2023
On the Equivalence of Consistency-Type Models: Consistency Models, Consistent Diffusion Models, and Fokker-Planck Regularization
The emergence of various notions of “consistency” in diffusion models ha...
research
∙
01/30/2023
Adversarially Slicing Generative Networks: Discriminator Slices Feature for One-Dimensional Optimal Transport
Generative adversarial networks (GANs) learn a target probability distri...
research
∙
01/30/2023
GibbsDDRM: A Partially Collapsed Gibbs Sampler for Solving Blind Inverse Problems with Denoising Diffusion Restoration
Pre-trained diffusion models have been successfully used as priors in a ...
research
∙
11/08/2022
Unsupervised vocal dereverberation with diffusion-based generative models
Removing reverb from reverberant music is a necessary technique to clean...
research
∙
10/09/2022
Regularizing Score-based Models with Score Fokker-Planck Equations
Score-based generative models learn a family of noise-conditional score ...
research
∙
05/16/2022
SQ-VAE: Variational Bayes on Discrete Representation with Self-annealed Stochastic Quantization
One noted issue of vector-quantized variational autoencoder (VQ-VAE) is ...
research
∙
02/04/2022
Robust Vector Quantized-Variational Autoencoder
Image generative models can learn the distributions of the training data...
research
∙
06/09/2020
Novelty Detection via Robust Variational Autoencoding
We propose a new method for novelty detection that can tolerate nontrivi...
research
∙
03/20/2020
Inverse Problems, Deep Learning, and Symmetry Breaking
In many physical systems, inputs related by intrinsic system symmetries ...
research
∙
03/30/2019