Scott Wisdom

Signal Processing · 2016–2023

A researcher in the Science corpus: 10 papers; trusts 66 researchers and is trusted by 11 researchers here, as inferred from the citation graph.

Subfields

• Signal Processing — 112 citations into it; #2,212 of 7,572 by trust here, #699 by citations
• Artificial Intelligence — 86 citations into it
• Speech & Audio — 58 citations into it; #564 of 1,076 by trust here, #552 by citations
• Computer Vision and Pattern Recognition — 42 citations into it
• Model Architectures — 19 citations into it
• Representation & Self-Supervised Learning — 18 citations into it
• Optimization & Training — 16 citations into it
• Computational Mechanics — 15 citations into it

Whom Scott Wisdom trusts overall

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

1. John R. Hershey
2. Jonathan Le Roux
3. Yoshua Bengio
4. Diederik P. Kingma
5. Yi Luo
6. Geoffrey E. Hinton
7. Yann LeCun
8. Sepp Hochreiter
9. Kaiming He
10. Hakan Erdogan

Who trusts Scott Wisdom overall

1. Hakan Erdogan
2. Eduardo Fonseca
3. Sebastian Braun
4. Nicolas Turpault
5. Xue Jiang
6. Shaojie Bai
7. Pavel Andreev
8. J. Tomczak
9. Piotr A. Sokól
10. Mario Lezcano Casado

Papers from Scott Wisdom's perspective

Ordered by how strongly the researchers Scott Wisdom 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. Long Short-Term Memory
5. Attention is All you Need (Neural Information Processing Systems)
6. Gradient-based learning applied to document recognition
7. ImageNet: A large-scale hierarchical image database
8. Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift (International Conference on Machine Learning)
9. Very Deep Convolutional Networks for Large-Scale Image Recognition (International Conference on Learning Representations)
10. Learning Multiple Layers of Features from Tiny Images

Their papers

• Full-Capacity Unitary Recurrent Neural Networks (2016) — 332 citations
• TokenSplit: Using Discrete Speech Representations for Direct, Refined, and Transcript-Conditioned Speech Separation and Recognition (2023) — 18 citations
• Self-Supervised Learning from Automatically Separated Sound Scenes (2021) — 13 citations
• What’s all the Fuss about Free Universal Sound Separation Data? (2020) — 96 citations
• Performance Study of a Convolutional Time-Domain Audio Separation Network for Real-Time Speech Denoising (2020) — 26 citations
• Improving Sound Event Detection in Domestic Environments using Sound Separation (2020) — 54 citations
• Universal Sound Separation (2019) — 209 citations
• Differentiable Consistency Constraints for Improved Deep Speech Enhancement (2018) — 131 citations
• SDR – Half-baked or Well Done? (2018) — 1,662 citations
• Interpretable Recurrent Neural Networks Using Sequential Sparse Recovery (2016) — 37 citations