Vadim Popov

17 papers A* 3A 4Misc 2Journal 6Unranked 2
YearRankTypeTitle / Venue / Authors
2026 — conf
AudioSAE: Towards Understanding of Audio-Processing Models with Sparse AutoEncoders.
EACL (Volume 1: Long Papers)
Georgii Aparin, Tasnima Sadekova, Alexey D. Rukhovich, Assel Yermekova, Laida Kushnareva, Vadim Popov, Kristian Kuznetsov, Irina Piontkovskaya
2026 J jnl
AudioSAE: Towards Understanding of Audio-Processing Models with Sparse AutoEncoders.
CoRR
Georgii Aparin, Tasnima Sadekova, Alexey D. Rukhovich, Assel Yermekova, Laida Kushnareva, Vadim Popov, Kristian Kuznetsov, Irina Piontkovskaya
2025 A* conf
Improved Sampling Algorithms for Lévy-Itô Diffusion Models.
ICLR
Vadim Popov, Assel Yermekova, Tasnima Sadekova, Artem Khrapov, Mikhail Sergeevich Kudinov
2024 J jnl
Improving Diffusion Models's Data-Corruption Resistance using Scheduled Pseudo-Huber Loss.
CoRR
Artem Khrapov, Vadim Popov, Tasnima Sadekova, Assel Yermekova, Mikhail A. Kudinov
2024 A conf
PitchFlow: adding pitch control to a Flow-matching based TTS model.
INTERSPEECH
Tasnima Sadekova, Mikhail A. Kudinov, Vadim Popov, Assel Yermekova, Artem Khrapov
2023 Misc conf
Optimal Transport in Diffusion Modeling for Conversion Tasks in Audio Domain.
ICASSP
Vadim Popov, Amantur Amatov, Mikhail A. Kudinov, Vladimir Gogoryan, Tasnima Sadekova, Ivan Vovk
2022 A conf
A Unified System for Voice Cloning and Voice Conversion through Diffusion Probabilistic Modeling.
INTERSPEECH
Tasnima Sadekova, Vladimir Gogoryan, Ivan Vovk, Vadim Popov, Mikhail A. Kudinov, Jiansheng Wei
2022 A* conf
Diffusion-Based Voice Conversion with Fast Maximum Likelihood Sampling Scheme.
ICLR
Vadim Popov, Ivan Vovk, Vladimir Gogoryan, Tasnima Sadekova, Mikhail Sergeevich Kudinov, Jiansheng Wei
2022 A conf
Fast Grad-TTS: Towards Efficient Diffusion-Based Speech Generation on CPU.
INTERSPEECH
Ivan Vovk, Tasnima Sadekova, Vladimir Gogoryan, Vadim Popov, Mikhail A. Kudinov, Jiansheng Wei
2021 J jnl
Diffusion-Based Voice Conversion with Fast Maximum Likelihood Sampling Scheme.
CoRR
Vadim Popov, Ivan Vovk, Vladimir Gogoryan, Tasnima Sadekova, Mikhail A. Kudinov, Jiansheng Wei
2021 A* conf
Grad-TTS: A Diffusion Probabilistic Model for Text-to-Speech.
ICML
Vadim Popov, Ivan Vovk, Vladimir Gogoryan, Tasnima Sadekova, Mikhail A. Kudinov
2021 J jnl
Grad-TTS: A Diffusion Probabilistic Model for Text-to-Speech.
CoRR
Vadim Popov, Ivan Vovk, Vladimir Gogoryan, Tasnima Sadekova, Mikhail A. Kudinov
2020 A conf
Fast and Lightweight On-Device TTS with Tacotron2 and LPCNet.
INTERSPEECH
Vadim Popov, Stanislav Kamenev, Mikhail A. Kudinov, Sergey Repyevsky, Tasnima Sadekova, Vitalii Bushaev, Vladimir Kryzhanovskiy, Denis Parkhomenko
2020 Misc conf
Gaussian Lpcnet for Multisample Speech Synthesis.
ICASSP
Vadim Popov, Mikhail A. Kudinov, Tasnima Sadekova
2018 — conf
Distributed Fine-tuning of Language Models on Private Data.
ICLR (Poster)
Vadim Popov, Mikhail A. Kudinov, Irina Piontkovskaya, Petr Vytovtov, Alex Nevidomsky
2018 J jnl
Fine-tuning of Language Models with Discriminator.
CoRR
Vadim Popov, Mikhail A. Kudinov
2017 J jnl
Differentially Private Distributed Learning for Language Modeling Tasks.
CoRR
Vadim Popov, Mikhail A. Kudinov, Irina Piontkovskaya, Petr Vytovtov, Alex Nevidomsky