| Digital Peter: New dataset, competition and handwriting recognition methods M Potanin, D Dimitrov, A Shonenkov, V Bataev, D Karachev, ... Proceedings of the 6th International Workshop on Historical Document Imaging …, 2021 | 24 | 2021 |
| The STC system for the CHiME 2018 challenge I Medennikov, I Sorokin, A Romanenko, D Popov, Y Khokhlov, T Prisyach, ... Proc. CHiME-5 Workshop, 2018 | 16 | 2018 |
| R-Vectors: New Technique for Adaptation to Room Acoustics. YY Khokhlov, A Zatvornitskiy, I Medennikov, I Sorokin, T Prisyach, ... INTERSPEECH, 1243-1247, 2019 | 14 | 2019 |
| Exploring end-to-end techniques for low-resource speech recognition V Bataev, M Korenevsky, I Medennikov, A Zatvornitskiy Speech and Computer: 20th International Conference, SPECOM 2018, Leipzig …, 2018 | 14 | 2018 |
| The STC ASR System for the VOiCES from a Distance Challenge 2019. I Medennikov, YY Khokhlov, A Romanenko, I Sorokin, A Mitrofanov, ... INTERSPEECH, 2453-2457, 2019 | 10 | 2019 |
| Text-only domain adaptation for end-to-end asr using integrated text-to-mel-spectrogram generator V Bataev, R Korostik, E Shabalin, V Lavrukhin, B Ginsburg arXiv preprint arXiv:2302.14036, 2023 | 5 | 2023 |
| Speed of Light Exact Greedy Decoding for RNN-T Speech Recognition Models on GPU D Galvez, V Bataev, H Xu, T Kaldewey arXiv preprint arXiv:2406.03791, 2024 | 1 | 2024 |
| Techniques for Vocabulary Expansion in Hybrid Speech Recognition Systems N Malkovsky, V Bataev, D Sviridkin, N Kizhaeva, A Laptev, I Valiev, ... arXiv preprint arXiv:2003.09024, 2020 | 1 | 2020 |
| Fast Context-Biasing for CTC and Transducer ASR models with CTC-based Word Spotter A Andrusenko, A Laptev, V Bataev, V Lavrukhin, B Ginsburg arXiv preprint arXiv:2406.07096, 2024 | | 2024 |
| Label-Looping: Highly Efficient Decoding for Transducers V Bataev, H Xu, D Galvez, V Lavrukhin, B Ginsburg arXiv preprint arXiv:2406.06220, 2024 | | 2024 |
| Hybrid language models for conversational ai systems and applications V Bataev, R Korostik, E Shabalin, VS Lavrukhin, B Ginsburg US Patent App. 18/468,086, 2024 | | 2024 |
| Powerful and Extensible WFST Framework for Rnn-Transducer Losses A Laptev, V Bataev, I Gitman, B Ginsburg ICASSP 2023-2023 IEEE International Conference on Acoustics, Speech and …, 2023 | | 2023 |
Ivan MedennikovNVIDIA在 nvidia.com 的电子邮件经过验证
