Jan Skoglund
Signal Processing · 2012–2023
A researcher in the Science corpus: 15 papers; trusts 310 researchers and is trusted by 155 researchers here, as inferred from the citation graph.
Subfields
- Signal Processing — 135 citations into it; #125 of 7,592 by trust here, #198 by citations
- Speech & Audio — 114 citations into it; #33 of 1,080 by trust here, #97 by citations
- Artificial Intelligence — 112 citations into it; #2,631 of 36,961 by trust here, #4,026 by citations
- Computer Vision and Pattern Recognition — 97 citations into it; #12,408 of 21,973 by trust here, #7,740 by citations
- Generative Models — 47 citations into it
- Evaluation & Benchmarks — 21 citations into it; #1,716 of 3,155 by trust here, #2,140 by citations
- Natural Language Processing — 18 citations into it; #714 of 5,725 by trust here, #1,825 by citations
- Cognitive Neuroscience — 13 citations into it; #8,040 of 11,026 by trust here, #6,865 by citations
Whom Jan Skoglund trusts overall
Their strongest outbound trust, strongest first, inferred from their citations.
- Jean-Marc Valin
- Aäron van den Oord
- Kyunghyun Cho
- Andrew Hines
- Yoshua Bengio
- Geoffrey E. Hinton
- W. Kleijn
- Nal Kalchbrenner
- Oriol Vinyals
- Diederik P. Kingma
Who trusts Jan Skoglund overall
- Alexandre D'efossez
- Jean-Marc Valin
- Jade Copet
- Hubert Siuzdak
- Andrew Hines
- Adam Polyak
- Neil Zeghidour
- Yossi Adi
- Slava Shechtman
- Xu Tan
Papers from Jan Skoglund's perspective
Ordered by how strongly the researchers Jan Skoglund 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)
- Attention is All you Need (Neural Information Processing Systems)
- Long Short-Term Memory
- Gradient-based learning applied to document recognition
- ImageNet: A large-scale hierarchical image database
- GENERATIVE ADVERSARIAL NETS
- Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift (International Conference on Machine Learning)
- Going deeper with convolutions
Their papers
- SoundStream: An End-to-End Neural Audio Codec (2021) — 1,407 citations
- LPCNET: Improving Neural Speech Synthesis through Linear Prediction (2018) — 500 citations
- Wavenet Based Low Rate Speech Coding (2017) — 154 citations
- Generative Speech Coding with Predictive Variance Regularization (2021) — 79 citations
- ViSQOL v3: An Open Source Production Ready Objective Speech and Audio Metric (2020) — 229 citations
- Robust Low Rate Speech Coding Based on Cloned Networks and Wavenet (2020) — 13 citations
- Improving Opus Low Bit Rate Quality with Neural Speech Synthesis (2019) — 41 citations
- LMCodec: A Low Bitrate Speech Codec with Causal Transformer Models (2023) — 31 citations
- A Real-Time Wideband Neural Vocoder at 1.6 kb/s Using LPCNet (2019) — 84 citations
- AMBIQUAL - a full reference objective quality metric for ambisonic spatial audio (2018) — 24 citations
- ViSQOL: an objective speech quality model (2015) — 202 citations
- ViSQOLAudio: An objective audio quality metric for low bitrate codecs. (2015) — 55 citations
- Perceived Audio Quality for Streaming Stereo Music (2014) — 14 citations
- Robustness of speech quality metrics to background noise and network degradations: Comparing ViSQOL, PESQ and POLQA (2013) — 42 citations
- ViSQOL: The Virtual Speech Quality Objective Listener (2012) — 75 citations