Follow
Vitaly Lavrukhin
Vitaly Lavrukhin
Verified email at nvidia.com
Title
Cited by
Cited by
Year
Quartznet: Deep automatic speech recognition with 1d time-channel separable convolutions
S Kriman, S Beliaev, B Ginsburg, J Huang, O Kuchaiev, V Lavrukhin, ...
ICASSP 2020-2020 IEEE International Conference on Acoustics, Speech and …, 2020
3042020
Jasper: An end-to-end convolutional neural acoustic model
J Li, V Lavrukhin, B Ginsburg, R Leary, O Kuchaiev, JM Cohen, H Nguyen, ...
arXiv preprint arXiv:1904.03288, 2019
2602019
Nemo: a toolkit for building ai applications using neural modules
O Kuchaiev, J Li, H Nguyen, O Hrinchuk, R Leary, B Ginsburg, S Kriman, ...
arXiv preprint arXiv:1909.09577, 2019
1992019
Stochastic gradient methods with layer-wise adaptive moments for training of deep networks
B Ginsburg, P Castonguay, O Hrinchuk, O Kuchaiev, V Lavrukhin, R Leary, ...
arXiv preprint arXiv:1905.11286, 2019
922019
Hi-fi multi-speaker english tts dataset
E Bakhturina, V Lavrukhin, B Ginsburg, Y Zhang
arXiv preprint arXiv:2104.01497, 2021
672021
Citrinet: Closing the gap between non-autoregressive and autoregressive end-to-end models for automatic speech recognition
S Majumdar, J Balam, O Hrinchuk, V Lavrukhin, V Noroozi, B Ginsburg
arXiv preprint arXiv:2104.01721, 2021
622021
Training neural speech recognition systems with synthetic speech augmentation
J Li, R Gadde, B Ginsburg, V Lavrukhin
arXiv preprint arXiv:1811.00707, 2018
582018
Mixed-precision training for nlp and speech recognition with openseq2seq
O Kuchaiev, B Ginsburg, I Gitman, V Lavrukhin, J Li, H Nguyen, C Case, ...
arXiv preprint arXiv:1805.10387, 2018
432018
SpeakerNet: 1D depth-wise separable convolutional network for text-independent speaker recognition and verification
NR Koluguri, J Li, V Lavrukhin, B Ginsburg
arXiv preprint arXiv:2010.12653, 2020
402020
Openseq2seq: extensible toolkit for distributed and mixed precision training of sequence-to-sequence models
O Kuchaiev, B Ginsburg, I Gitman, V Lavrukhin, C Case, P Micikevicius
Proceedings of Workshop for NLP Open Source Software (NLP-OSS), 41-46, 2018
392018
Spgispeech: 5,000 hours of transcribed financial audio for fully formatted end-to-end speech recognition
PK O'Neill, V Lavrukhin, S Majumdar, V Noroozi, Y Zhang, O Kuchaiev, ...
arXiv preprint arXiv:2104.02014, 2021
352021
Cross-language transfer learning, continuous learning, and domain adaptation for end-to-end automatic speech recognition
J Huang, O Kuchaiev, P O'Neill, V Lavrukhin, J Li, A Flores, G Kucsko, ...
arXiv preprint arXiv:2005.04290, 2020
212020
Cross-language transfer learning and domain adaptation for end-to-end automatic speech recognition
J Luo, J Wang, N Cheng, E Xiao, J Xiao, G Kucsko, P O’Neill, J Balam, ...
2021 IEEE International Conference on Multimedia and Expo (ICME), 1-6, 2021
172021
Training deep networks with stochastic gradient normalized by layerwise adaptive second moments
B Ginsburg, P Castonguay, O Hrinchuk, O Kuchaiev, V Lavrukhin, R Leary, ...
92019
A toolbox for construction and analysis of speech datasets
E Bakhturina, V Lavrukhin, B Ginsburg
arXiv preprint arXiv:2104.04896, 2021
72021
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
42023
Damage control during domain adaptation for transducer based automatic speech recognition
S Majumdar, S Acharya, V Lavrukhin, B Ginsburg
2022 IEEE Spoken Language Technology Workshop (SLT), 130-135, 2023
42023
Improving noise robustness of an end-to-end neural model for automatic speech recognition
J Balam, J Huang, V Lavrukhin, S Deng, S Majumdar, B Ginsburg
arXiv preprint arXiv:2010.12715, 2020
42020
Conformer-based target-speaker automatic speech recognition for single-channel audio
Y Zhang, KC Puvvada, V Lavrukhin, B Ginsburg
ICASSP 2023-2023 IEEE International Conference on Acoustics, Speech and …, 2023
22023
LibriSpeech-PC: Benchmark for Evaluation of Punctuation and Capitalization Capabilities of end-to-end ASR Models
A Meister, M Novikov, N Karpov, E Bakhturina, V Lavrukhin, B Ginsburg
2023 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU), 1-7, 2023
12023
The system can't perform the operation now. Try again later.
Articles 1–20