| Deep Voice 3: Scaling text-to-speech with convolutional sequence learning W Ping, K Peng, A Gibiansky, SO Arik, A Kannan, S Narang, J Raiman, ... International Conference on Learning Representations (ICLR), 2018 | 711* | 2018 |
| Deep Voice: Real-time neural text-to-speech SO Arik, M Chrzanowski, A Coates, G Diamos, A Gibiansky, Y Kang, X Li, ... International Conference on Machine Learning (ICML), 2017 | 673* | 2017 |
| Temporal fusion transformers for interpretable multi-horizon time series forecasting B Lim, SO Arik, N Loeff, T Pfister International Journal of Forecasting, 2021 | 544 | 2021 |
| TabNet: Attentive interpretable tabular learning SO Arik, T Pfister AAAI Conference on Artificial Intelligence (AAAI), 2021 | 544 | 2021 |
| Deep Voice 2: Multi-speaker neural text-to-speech SO Arik, G Diamos, A Gibiansky, J Miller, K Peng, W Ping, J Raiman, ... Neural Information Processing Systems (NeurIPS), 2017 | 524* | 2017 |
| Neural voice cloning with a few samples SO Arik, J Chen, K Peng, W Ping, Y Zhou Neural Information Processing Systems (NeurIPS), 2018 | 324 | 2018 |
| Fully automated quantitative cephalometry using convolutional neural networks SÖ Arık, B Ibragimov, L Xing Journal of Medical Imaging 4 (1), 014501-014501, 2017 | 190 | 2017 |
| On completeness-aware concept-based explanations in deep neural networks CK Yeh, B Kim, SO Arik, CL Li, T Pfister, P Ravikumar Neural Information Processing Systems (NeurIPS), 2020 | 184* | 2020 |
| Convolutional recurrent neural networks for small-footprint keyword spotting SO Arik, M Kliegl, R Child, J Hestness, A Gibiansky, C Fougner, ... Interspeech, 2017 | 172* | 2017 |
| Effect of mode coupling on signal processing complexity in mode-division multiplexing SÖ Arik, D Askarov, JM Kahn Journal of Lightwave Technology 31 (3), 423-431, 2012 | 163 | 2012 |
| Evaluation of individual and ensemble probabilistic forecasts of COVID-19 mortality in the United States EY Cramer, EL Ray, VK Lopez, J Bracher, A Brennen, ... Proceedings of the National Academy of Sciences 119 (15), e2113561119, 2022 | 150 | 2022 |
| MIMO signal processing for mode-division multiplexing SO Arik, J Kahn, K Ho IEEE Signal Processing Magazine 31 (2), 25-34, 2014 | 144 | 2014 |
| High-dimensional modulation for coherent optical communications systems DS Millar, T Koike-Akino, SÖ Arık, K Kojima, K Parsons, T Yoshida, ... Optics express 22 (7), 8798-8812, 2014 | 134 | 2014 |
| Adaptive frequency-domain equalization in mode-division multiplexing systems SÖ Arık, D Askarov, JM Kahn Journal of Lightwave Technology 32 (10), 1841-1852, 2014 | 117 | 2014 |
| Consistency-based semi-supervised active learning: towards minimizing labeling cost M Gao, Z Zhang, G Yu, SO Arik, LS Davis, T Pfister European Conference on Computer Vision (ECCV), 2020 | 114 | 2020 |
| Distilling effective supervision from severe label noise Z Zhang, H Zhang, SO Arik, H Lee, T Pfister Conference on Computer Vision and Pattern Recognition (CVPR), 2020 | 112 | 2020 |
| Data valuation using reinforcement learning J Yoon, SO Arik, T Pfister International Conference on Machine Learning (ICML), 2020 | 104 | 2020 |
| Fast spectrogram inversion using multi-head convolutional neural networks SO Arik, H Jun, G Diamos IEEE Signal Processing Letters, 2018 | 100 | 2018 |
| Interpretable sequence learning for COVID-19 forecasting SO Arik, CL Li, J Yoon, R Sinha, A Epshteyn, LT Le, V Menon, S Singh, ... Neural Information Processing Systems (NeurIPS), 2020 | 78 | 2020 |
| Nested hierarchical transformer: Towards accurate, data-efficient and interpretable visual understanding Z Zhang, H Zhang, L Zhao, T Chen, SO Arik, T Pfister AAAI Conference on Artificial Intelligence (AAAI), 2022 | 67 | 2022 |
Tomas PfisterHead of AI Research @ Google CloudVerified email at google.com
