| Regularization of neural networks using dropconnect L Wan, M Zeiler, S Zhang, Y Le Cun, R Fergus International conference on machine learning, 1058-1066, 2013 | 3415 | 2013 |
| Generalized end-to-end loss for speaker verification L Wan, Q Wang, A Papir, IL Moreno 2018 IEEE International Conference on Acoustics, Speech and Signal …, 2018 | 1092 | 2018 |
| Speaker diarization with LSTM Q Wang, C Downey, L Wan, PA Mansfield, IL Moreno 2018 IEEE International conference on acoustics, speech and signal …, 2018 | 422 | 2018 |
| Distant supervision for relation extraction with an incomplete knowledge base B Min, R Grishman, L Wan, C Wang, D Gondek Proceedings of the 2013 Conference of the North American Chapter of the …, 2013 | 334 | 2013 |
| Attention-based models for text-dependent speaker verification FAR rahman Chowdhury, Q Wang, IL Moreno, L Wan 2018 IEEE International Conference on Acoustics, Speech and Signal …, 2018 | 209 | 2018 |
| Density-based clustering of data streams at multiple resolutions L Wan, WK Ng, XH Dang, PS Yu, K Zhang ACM Transactions on Knowledge discovery from Data (TKDD) 3 (3), 1-28, 2009 | 206 | 2009 |
| End-to-end integration of a convolution network, deformable parts model and non-maximum suppression L Wan, D Eigen, R Fergus Proceedings of the IEEE Conference on Computer Vision and Pattern …, 2015 | 114 | 2015 |
| Privacy-preservation for gradient descent methods L Wan, WK Ng, S Han, VCS Lee Proceedings of the 13th ACM SIGKDD international conference on Knowledge …, 2007 | 113 | 2007 |
| Heterogeneous ensemble for feature drifts in data streams HL Nguyen, YK Woon, WK Ng, L Wan Advances in Knowledge Discovery and Data Mining: 16th Pacific-Asia …, 2012 | 107 | 2012 |
| Privacy-preserving gradient-descent methods S Han, WK Ng, L Wan, VCS Lee IEEE transactions on knowledge and data engineering 22 (6), 884-899, 2009 | 99 | 2009 |
| Personal VAD: Speaker-conditioned voice activity detection S Ding, Q Wang, S Chang, L Wan, IL Moreno arXiv preprint arXiv:1908.04284, 2019 | 93 | 2019 |
| A hybrid neural network-latent topic model L Wan, L Zhu, R Fergus Artificial Intelligence and Statistics, 1287-1294, 2012 | 60 | 2012 |
| Speaker verification IL Moreno, L Wan, Q Wang US Patent App. 15/211,317, 2018 | 39 | 2018 |
| Neural networks for speaker verification H Sak, IL Moreno, AS Papir, L Wan, Q Wang US Patent 10,325,602, 2019 | 29 | 2019 |
| Links: A high-dimensional online clustering method PA Mansfield, Q Wang, C Downey, L Wan, IL Moreno arXiv preprint arXiv:1801.10123, 2018 | 28 | 2018 |
| Tuplemax loss for language identification L Wan, P Sridhar, Y Yu, Q Wang, IL Moreno ICASSP 2019-2019 IEEE International Conference on Acoustics, Speech and …, 2019 | 25 | 2019 |
| Multi-microphone adaptive noise cancellation for robust hotword detection Y Huang, TZ Shabestary, A Gruenstein, L Wan | 14 | 2019 |
| Signal combination for language identification S Wang, L Wan, Y Yu, IL Moreno arXiv preprint arXiv:1910.09687, 2019 | 13 | 2019 |
| Speaker diartzation using an end-to-end model Q Wang, Y Sheth, IL Moreno, L Wan US Patent 11,545,157, 2023 | 12 | 2023 |
| Improving speaker verification across locations, languages, and/or dialects IL Moreno, L Wan, Q Wang US Patent 10,403,291, 2019 | 12 | 2019 |
Rob FergusResearch Scientist, DeepMind. Professor of Computer Science, New York UniversityVerified email at cs.nyu.edu
