← Search

Mikhail Sergeevich Kudinov

2 accepted papers

2025

Improved Sampling Algorithms for Lévy-Itô Diffusion Models

ICLR 2025poster

Lévy-Itô denoising diffusion models relying on isotropic α-stable noise instead of Gaussian distribution have recently been shown to improve performance of conventional diffusion models in image generation on imbalanced datasets while performing comparably in the standard settings. However, the stoc…

Cited by 0SourcePDFScholar
2022

Diffusion-Based Voice Conversion with Fast Maximum Likelihood Sampling Scheme

ICLR 2022oral

Voice conversion is a common speech synthesis task which can be solved in different ways depending on a particular real-world scenario. The most challenging one often referred to as one-shot many-to-many voice conversion consists in copying target voice from only one reference utterance in the most…