604 citations · 2.5k across the 63 of their papers we have counts for
3 papers · 1 filter
UnDiff: Unsupervised Voice Restoration with Unconditional Diffusion Model
Anastasiia Iashchenko, Pavel Andreev, Ivan Shchekotov +2
This paper introduces UnDiff, a diffusion probabilistic model capable of solving various speech inverse tasks. Being once trained for speech waveform generation in an unconditional…
FFC-SE: Fast Fourier Convolution for Speech Enhancement
Ivan Shchekotov, Pavel Andreev, Oleg Ivanov +2
Fast Fourier convolution (FFC) is the recently proposed neural operator showing promising performance in several computer vision problems. The FFC operator allows employing large r…
HiFi++: a Unified Framework for Bandwidth Extension and Speech Enhancement
Pavel Andreev, Aibek Alanov, Oleg Ivanov +1
Generative adversarial networks have recently demonstrated outstanding performance in neural vocoding outperforming best autoregressive and flow-based models. In this paper, we sho…