| Grad-tts: A diffusion probabilistic model for text-to-speech V Popov, I Vovk, V Gogoryan, T Sadekova, M Kudinov International Conference on Machine Learning, 8599-8608, 2021 | 492 | 2021 |
| Diffusion-based voice conversion with fast maximum likelihood sampling scheme V Popov, I Vovk, V Gogoryan, T Sadekova, M Kudinov, J Wei arXiv preprint arXiv:2109.13821, 2021 | 104 | 2021 |
| Gaussian LPCNet for multisample speech synthesis V Popov, M Kudinov, T Sadekova ICASSP 2020-2020 IEEE International Conference on Acoustics, Speech and …, 2020 | 18 | 2020 |
| Distributed fine-tuning of language models on private data V Popov, M Kudinov, I Piontkovskaya, P Vytovtov, A Nevidomsky International Conference on Learning Representations, 2018 | 17 | 2018 |
| Fast and Lightweight On-Device TTS with Tacotron2 and LPCNet. V Popov, S Kamenev, MA Kudinov, S Repyevsky, T Sadekova, V Bushaev, ... INTERSPEECH, 220-224, 2020 | 12 | 2020 |
| A Unified System for Voice Cloning and Voice Conversion through Diffusion Probabilistic Modeling. T Sadekova, V Gogoryan, I Vovk, V Popov, MA Kudinov, J Wei INTERSPEECH, 3003-3007, 2022 | 10 | 2022 |
| Fast Grad-TTS: Towards Efficient Diffusion-Based Speech Generation on CPU. I Vovk, T Sadekova, V Gogoryan, V Popov, MA Kudinov, J Wei Interspeech, 838-842, 2022 | 9 | 2022 |
| Optimal transport in diffusion modeling for conversion tasks in audio domain V Popov, A Amatov, M Kudinov, V Gogoryan, T Sadekova, I Vovk ICASSP 2023-2023 IEEE International Conference on Acoustics, Speech and …, 2023 | 6 | 2023 |
| Differentially private distributed learning for language modeling tasks V Popov, M Kudinov, I Piontkovskaya, P Vytovtov, A Nevidomsky arXiv preprint arXiv:1712.07473, 2017 | 3 | 2017 |
| Fine-tuning of language models with discriminator V Popov, M Kudinov arXiv preprint arXiv:1811.04623, 2018 | 2 | 2018 |
| Distributed training of machine learning models for personalization MS Kudinov, I Piontkovskaya, AY Nevidomskii, VS Popov, PK Vytovtov, ... US Patent App. 17/413,897, 2022 | 1 | 2022 |
| Improving Diffusion Models's Data-Corruption Resistance using Scheduled Pseudo-Huber Loss A Khrapov, V Popov, T Sadekova, A Yermekova, M Kudinov arXiv preprint arXiv:2403.16728, 2024 | | 2024 |
| Efficient Strategies of Few-Shot On-Device Voice Cloning T Sadekova, V Popov, V Gogoryan, I Vovk, A Drogolyub, D Polubotko, ... | | |
