Vitaly Lavrukhin
Identifiers
- name variant Vitaly Lavrukhin 0.60 · backfill
Papers (40)
- Hierarchical Policy Optimization for Simultaneous Translation of Unbounded Speech cs.CL · 2026 · author #4
- Reducing the Offline-Streaming Gap for Unified ASR Transducer with Consistency Regularization eess.AS · 2026 · author #5
- Nemotron 3 Super: Open, Efficient Mixture-of-Experts Hybrid Mamba-Transformer Model for Agentic Reasoning cs.LG · 2026 · author #506
- NVIDIA Nemotron 3: Efficient and Open Intelligence cs.CL · 2025 · author #329
- NVIDIA Nemotron Nano 2: An Accurate and Efficient Hybrid Mamba-Transformer Reasoning Model cs.CL · 2025 · author #200
- FlexCTC: GPU-powered CTC Beam Decoding With Advanced Contextual Abilities eess.AS · 2025 · author #5
- TurboBias: Universal ASR Context-Biasing powered by GPU-accelerated Phrase-Boosting Tree eess.AS · 2025 · author #4
- Open Automatic Speech Recognition Models for Classical and Modern Standard Arabic cs.CL · 2025 · author #4
- Unified Semi-Supervised Pipeline for Automatic Speech Recognition eess.AS · 2025 · author #4
- Pushing the Limits of Beam Search Decoding for Transducer-based ASR models eess.AS · 2025 · author #5
- NGPU-LM: GPU-Accelerated N-Gram Language Model for Context-Biasing in Greedy ASR Decoding eess.AS · 2025 · author #5
- Granary: Speech Recognition and Translation Dataset in 25 European Languages cs.CL · 2025 · author #10
- Training and Inference Efficiency of Encoder-Decoder Speech Models cs.CL · 2025 · author #8
- TTS-Transducer: End-to-End Speech Synthesis with Neural Transducer eess.AS · 2025 · author #3
- Methods to Increase the Amount of Data for Speech Recognition for Low Resource Languages cs.SD · 2025 · author #7
- Anticipating Future with Large Language Model for Simultaneous Machine Translation cs.CL · 2024 · author #4
- EMMeTT: Efficient Multimodal Machine Translation Training cs.CL · 2024 · author #9
- Chain-of-Thought Prompting for Speech Translation cs.CL · 2024 · author #6
- Less is More: Accurate Speech Recognition & Translation without Web-Scale Data cs.CL · 2024 · author #10
- Fast Context-Biasing for CTC and Transducer ASR models with CTC-based Word Spotter eess.AS · 2024 · author #4
- Label-Looping: Highly Efficient Decoding for Transducers eess.AS · 2024 · author #4
- LibriSpeech-PC: Benchmark for Evaluation of Punctuation and Capitalization Capabilities of end-to-end ASR Models cs.CL · 2023 · author #5
- A Chat About Boring Problems: Studying GPT-based text normalization cs.CL · 2023 · author #4
- Conformer-based Target-Speaker Automatic Speech Recognition for Single-Channel Audio cs.SD · 2023 · author #3
- Confidence-based Ensembles of End-to-End Speech Recognition Models eess.AS · 2023 · author #2
- Text-only domain adaptation for end-to-end ASR using integrated text-to-mel-spectrogram generator eess.AS · 2023 · author #4
- Damage Control During Domain Adaptation for Transducer Based Automatic Speech Recognition cs.SD · 2022 · author #3
- A Toolbox for Construction and Analysis of Speech Datasets eess.AS · 2021 · author #2
- SPGISpeech: 5,000 hours of transcribed financial audio for fully formatted end-to-end speech recognition cs.CL · 2021 · author #2
- Citrinet: Closing the Gap between Non-Autoregressive and Autoregressive End-to-End Models for Automatic Speech Recognition eess.AS · 2021 · author #4
- Hi-Fi Multi-Speaker English TTS Dataset eess.AS · 2021 · author #2
- Improving Noise Robustness of an End-to-End Neural Model for Automatic Speech Recognition eess.AS · 2020 · author #3
- SpeakerNet: 1D Depth-wise Separable Convolutional Network for Text-Independent Speaker Recognition and Verification eess.AS · 2020 · author #3
- Cross-Language Transfer Learning, Continuous Learning, and Domain Adaptation for End-to-End Automatic Speech Recognition eess.AS · 2020 · author #4
- QuartzNet: Deep Automatic Speech Recognition with 1D Time-Channel Separable Convolutions eess.AS · 2019 · author #6
- NeMo: a toolkit for building AI applications using Neural Modules cs.LG · 2019 · author #9
- Stochastic Gradient Methods with Layer-wise Adaptive Moments for Training of Deep Networks cs.LG · 2019 · author #5
- Jasper: An End-to-End Convolutional Neural Acoustic Model eess.AS · 2019 · author #2
- Training Neural Speech Recognition Systems with Synthetic Speech Augmentation cs.CL · 2018 · author #4
- Mixed-Precision Training for NLP and Speech Recognition with OpenSeq2Seq cs.CL · 2018 · author #4
Mentions
- 2508.07315 #5 · arxiv_oai · confidence 0.70 Vitaly Lavrukhin
- 2508.07014 #4 · arxiv_oai · confidence 0.70 Vitaly Lavrukhin
- 2507.13977 #4 · arxiv_oai · confidence 0.70 Vitaly Lavrukhin
- 2506.07659 #4 · arxiv_oai · confidence 0.70 Vitaly Lavrukhin
- 2506.00185 #5 · arxiv_oai · confidence 0.70 Vitaly Lavrukhin
- 2410.22499 #4 · arxiv_oai · confidence 0.70 Vitaly Lavrukhin
- 2505.22857 #5 · arxiv_oai · confidence 0.70 Vitaly Lavrukhin
- 2505.13404 #10 · arxiv_oai · confidence 0.70 Vitaly Lavrukhin
- 2501.06320 #3 · arxiv_oai · confidence 0.70 Vitaly Lavrukhin
- 2409.11538 #6 · arxiv_oai · confidence 0.70 Vitaly Lavrukhin
- 2503.05931 #8 · arxiv_oai · confidence 0.70 Vitaly Lavrukhin
- 2501.14788 #7 · arxiv_oai · confidence 0.70 Vitaly Lavrukhin
- 2406.06220 #4 · arxiv_oai · confidence 0.70 Vitaly Lavrukhin
- 2409.13523 #9 · arxiv_oai · confidence 0.70 Vitaly Lavrukhin
- 2302.14036 #4 · arxiv_oai · confidence 0.70 Vitaly Lavrukhin
- 2406.19674 #10 · arxiv_oai · confidence 0.70 Vitaly Lavrukhin
- 2406.07096 #4 · arxiv_oai · confidence 0.70 Vitaly Lavrukhin
- 2309.13426 #4 · arxiv_oai · confidence 0.70 Vitaly Lavrukhin
- 2310.02943 #5 · arxiv_oai · confidence 0.70 Vitaly Lavrukhin
- 2306.15824 #2 · arxiv_oai · confidence 0.70 Vitaly Lavrukhin
- 2308.05218 #3 · arxiv_oai · confidence 0.70 Vitaly Lavrukhin
- 2210.03255 #3 · arxiv_oai · confidence 0.70 Vitaly Lavrukhin
- 2104.04896 #2 · arxiv_oai · confidence 0.70 Vitaly Lavrukhin
- 2104.01497 #2 · arxiv_oai · confidence 0.70 Vitaly Lavrukhin
- 2104.02014 #2 · arxiv_oai · confidence 0.70 Vitaly Lavrukhin
- 2104.01721 #4 · arxiv_oai · confidence 0.70 Vitaly Lavrukhin
- 2010.12715 #3 · arxiv_oai · confidence 0.70 Vitaly Lavrukhin
- 2010.12653 #3 · arxiv_oai · confidence 0.70 Vitaly Lavrukhin
- 2005.04290 #4 · arxiv_oai · confidence 0.70 Vitaly Lavrukhin
- 1905.11286 #5 · arxiv_oai · confidence 0.70 Vitaly Lavrukhin
- 1910.10261 #6 · arxiv_oai · confidence 0.70 Vitaly Lavrukhin
- 1909.09577 #9 · arxiv_oai · confidence 0.70 Vitaly Lavrukhin
- 1904.03288 #2 · arxiv_oai · confidence 0.70 Vitaly Lavrukhin
- 1805.10387 #4 · arxiv_oai · confidence 0.70 Vitaly Lavrukhin
- 1811.00707 #4 · arxiv_oai · confidence 0.70 Vitaly Lavrukhin
- 2508.14444 #200 · arxiv_oai · confidence 0.70 Vitaly Lavrukhin
- 2512.20856 #329 · arxiv_oai · confidence 0.70 Vitaly Lavrukhin
Frequent Coauthors
- Boris Ginsburg 38 shared papers
- Oleksii Hrinchuk 11 shared papers
- Oleksii Kuchaiev 10 shared papers
- Jagadeesh Balam 9 shared papers
- Jason Li 9 shared papers
- Vladimir Bataev 9 shared papers
- Somshubra Majumdar 8 shared papers
- Andrei Andrusenko 7 shared papers
- Evelina Bakhturina 7 shared papers
- Jocelyn Huang 6 shared papers
- Lilit Grigoryan 6 shared papers
- Nikolay Karpov 6 shared papers
- Shuoyang Ding 6 shared papers
- Igor Gitman 5 shared papers
- Krishna C. Puvvada 5 shared papers
- Samuel Kriman 5 shared papers
- Vahid Noroozi 5 shared papers
- Yang Zhang 5 shared papers
- Huyen Nguyen 4 shared papers
- Matvei Novikov 4 shared papers