Jonathan Le Roux
Signal Processing · 2007–2020
A researcher in the Science corpus: 28 papers; trusts 492 researchers and is trusted by 323 researchers here, as inferred from the citation graph.
Subfields
- Signal Processing — 241 citations into it; #62 of 7,592 by trust here, #66 by citations
- Artificial Intelligence — 229 citations into it; #1,892 of 36,961 by trust here, #1,787 by citations
- Speech & Audio — 110 citations into it; #72 of 1,080 by trust here, #79 by citations
- Computational Mechanics — 58 citations into it; #2,648 of 10,021 by trust here, #1,826 by citations
- Computer Vision and Pattern Recognition — 57 citations into it; #21,501 of 21,973 by trust here, #14,133 by citations
- Model Architectures — 38 citations into it; #446 of 2,288 by trust here, #649 by citations
- Cognitive Neuroscience — 36 citations into it; #965 of 11,026 by trust here, #1,670 by citations
- Natural Language Processing — 34 citations into it
Whom Jonathan Le Roux trusts overall
Their strongest outbound trust, strongest first, inferred from their citations.
- John R. Hershey
- Zhuo Chen
- Yi Luo
- Geoffrey E. Hinton
- Emmanuel Vincent
- Yoshua Bengio
- Radford M. Neal
- Francis R. Bach
- Hakan Erdogan
- Alex Graves
Who trusts Jonathan Le Roux overall
- Zhong-Qiu Wang
- Yi Luo
- John R. Hershey
- Scott Wisdom
- Shinji Watanabe
- Zhuo Chen
- Hakan Erdogan
- Deliang Wang
- Gordon Wichern
- Dong Yu
Papers from Jonathan Le Roux's perspective
Ordered by how strongly the researchers Jonathan Le Roux trusts endorse each paper. Same corpus, a different order for every researcher.
- Deep Residual Learning for Image Recognition (Computer Vision and Pattern Recognition)
- ImageNet classification with deep convolutional neural networks
- Adam: A Method for Stochastic Optimization (International Conference on Learning Representations)
- Long Short-Term Memory
- Attention is All you Need (Neural Information Processing Systems)
- Gradient-based learning applied to document recognition
- ImageNet: A large-scale hierarchical image database
- Very Deep Convolutional Networks for Large-Scale Image Recognition (International Conference on Learning Representations)
- Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift (International Conference on Machine Learning)
- Neural Machine Translation by Jointly Learning to Align and Translate (International Conference on Learning Representations)
Their papers
- Deep clustering: Discriminative embeddings for segmentation and separation (2015) — 1,455 citations
- Full-Capacity Unitary Recurrent Neural Networks (2016) — 332 citations
- Discriminative Training for Large-Vocabulary Speech Recognition Using Minimum Classification Error (2007) — 638 citations
- Deep Unfolding: Model-Based Inspiration of Novel Deep Architectures (2014) — 492 citations
- Cycle-consistency Training for End-to-end Speech Recognition (2018) — 90 citations
- Speech Enhancement with LSTM Recurrent Neural Networks and its Application to Noise-Robust ASR (2015) — 650 citations
- Single-Channel Multi-Speaker Separation Using Deep Clustering (2016) — 454 citations
- Discriminatively trained recurrent neural networks for single-channel speech separation (2014) — 306 citations
- The MERL/MELCO/TUM system for the REVERB Challenge using Deep Recurrent Neural Network Feature Enhancement (2014) — 44 citations
- The second ‘chime’ speech separation and recognition challenge: Datasets, tasks and baselines (2013) — 315 citations
- WHAM!: Extending Speech Separation to Noisy Environments (2019) — 507 citations
- WHAMR!: Noisy and Reverberant Single-Channel Speech Separation (2019) — 227 citations
- Student-teacher network learning with enhanced features (2017) — 89 citations
- Unsupervised Domain Adaptation for Speech Recognition via Uncertainty Driven Self-Training (2020) — 74 citations
- The Phasebook: Building Complex Masks via Discrete Representations for Source Separation (2019) — 14 citations
- Universal Sound Separation (2019) — 209 citations
- End-to-End Speech Separation with Unfolded Iterative Phase Reconstruction (2018) — 134 citations
- Bootstrapping Single-channel Source Separation via Unsupervised Spatial Clustering on Stereo Mixtures (2018) — 39 citations
- SDR – Half-baked or Well Done? (2018) — 1,662 citations
- Alternative Objective Functions for Deep Clustering (2018) — 191 citations