Vitaly Lavrukhin

Artificial Intelligence · 2018–2021

A researcher in the Science corpus: 9 papers; trusts 88 researchers and is trusted by 11 researchers here, as inferred from the citation graph.

Subfields

• Artificial Intelligence — 144 citations into it; #13,782 of 35,345 by trust here, #8,007 by citations
• Natural Language Processing — 85 citations into it; #4,488 of 5,688 by trust here, #2,767 by citations
• Computer Vision and Pattern Recognition — 60 citations into it
• Signal Processing — 57 citations into it; #4,981 of 7,572 by trust here, #1,820 by citations
• Speech & Audio — 46 citations into it; #832 of 1,076 by trust here, #539 by citations
• Optimization & Training — 41 citations into it
• Model Architectures — 37 citations into it; #2,088 of 2,278 by trust here, #1,620 by citations
• Evaluation & Benchmarks — 21 citations into it

Whom Vitaly Lavrukhin trusts overall

Their strongest outbound trust, strongest first, inferred from their citations.

1. Alex Graves
2. Geoffrey E. Hinton
3. Diederik P. Kingma
4. Yoshua Bengio
5. Ilya Sutskever
6. Alex Krizhevsky
7. Ronan Collobert
8. Kaiming He
9. Jimmy Ba
10. Yann LeCun

Who trusts Vitaly Lavrukhin overall

1. Adam Polyak
2. James Betker
3. Boris Ginsburg
4. Stanislav Beliaev
5. Heeseung Kim
6. Hubert Siuzdak
7. Lior Wolf
8. Hyeong-Seok Choi
9. Jean-Marc Valin
10. Albert Zeyer

Papers from Vitaly Lavrukhin's perspective

Ordered by how strongly the researchers Vitaly Lavrukhin trusts endorse each paper. Same corpus, a different order for every researcher.

1. Deep Residual Learning for Image Recognition (Computer Vision and Pattern Recognition)
2. ImageNet classification with deep convolutional neural networks
3. Adam: A Method for Stochastic Optimization (International Conference on Learning Representations)
4. Attention is All you Need (Neural Information Processing Systems)
5. Long Short-Term Memory
6. Gradient-based learning applied to document recognition
7. Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift (International Conference on Machine Learning)
8. ImageNet: A large-scale hierarchical image database
9. Sequence to Sequence Learning with Neural Networks (Neural Information Processing Systems)
10. Neural Machine Translation by Jointly Learning to Align and Translate (International Conference on Learning Representations)

Their papers

• Jasper: An End-to-End Convolutional Neural Acoustic Model (2019) — 288 citations
• OpenSeq2Seq: Extensible Toolkit for Distributed and Mixed Precision Training of Sequence-to-Sequence Models (2018) — 33 citations
• NeMo: a toolkit for building AI applications using Neural Modules (2019) — 411 citations
• Quartznet: Deep Automatic Speech Recognition with 1D Time-Channel Separable Convolutions (2019) — 328 citations
• Mixed-Precision Training for NLP and Speech Recognition with OpenSeq2Seq (2018) — 52 citations
• Training Neural Speech Recognition Systems with Synthetic Speech Augmentation (2018) — 61 citations
• SPGISpeech: 5, 000 hours of transcribed financial audio for fully formatted end-to-end speech recognition (2021) — 113 citations
• Hi-Fi Multi-Speaker English TTS Dataset (2021) — 140 citations
• Stochastic Gradient Methods with Layer-wise Adaptive Moments for Training of Deep Networks (2019) — 108 citations