Jinyu Li
Artificial Intelligence · 2011–2024
A researcher in the Science corpus: 49 papers; trusts 1,999 researchers and is trusted by 747 researchers here, as inferred from the citation graph.
Subfields
- Artificial Intelligence — 1,328 citations into it; #1,220 of 36,961 by trust here, #1,208 by citations
- Signal Processing — 883 citations into it; #134 of 7,592 by trust here, #81 by citations
- Speech & Audio — 655 citations into it; #313 of 1,080 by trust here, #94 by citations
- Natural Language Processing — 277 citations into it; #2,582 of 5,725 by trust here, #1,388 by citations
- Computer Vision and Pattern Recognition — 211 citations into it
- Model Architectures — 178 citations into it; #854 of 2,288 by trust here, #1,115 by citations
- Representation & Self-Supervised Learning — 99 citations into it; #2,154 of 3,156 by trust here, #1,138 by citations
- Generative Models — 90 citations into it
Whom Jinyu Li trusts overall
Their strongest outbound trust, strongest first, inferred from their citations.
- Alex Graves
- Geoffrey E. Hinton
- Dong Yu
- Tara N. Sainath
- Yoshua Bengio
- Dzmitry Bahdanau
- Diederik P. Kingma
- Li Deng
- Alex Krizhevsky
- Oriol Vinyals
Who trusts Jinyu Li overall
- Dong Yu
- Li Deng
- Zhong Meng
- Zhuo Chen
- Yifan Gong
- Zhen Huang
- Sabato Marco Siniscalchi
- Rohit Prabhavalkar
- Arun Narayanan
- Shinji Watanabe
Papers from Jinyu Li's perspective
Ordered by how strongly the researchers Jinyu Li trusts endorse each paper. Same corpus, a different order for every researcher.
- Deep Residual Learning for Image Recognition (Computer Vision and Pattern Recognition)
- Adam: A Method for Stochastic Optimization (International Conference on Learning Representations)
- ImageNet classification with deep convolutional neural networks
- 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)
- Neural Machine Translation by Jointly Learning to Align and Translate (International Conference on Learning Representations)
- Sequence to Sequence Learning with Neural Networks (Neural Information Processing Systems)
Their papers
- Learning small-size DNN with output-distribution-based criteria (2014) — 311 citations
- Cross-language knowledge transfer using multilingual deep neural network with shared hidden layers (2013) — 686 citations
- Restructuring of deep neural network acoustic models with singular value decomposition (2013) — 448 citations
- Recent advances in deep learning for speech research at Microsoft (2013) — 820 citations
- Feature Learning in Deep Neural Networks - A Study on Speech Recognition Tasks (2013) — 266 citations
- An Overview of Noise-Robust Automatic Speech Recognition (2014) — 614 citations
- Improving wideband speech recognition using mixed-bandwidth training data in CD-DNN-HMM (2012) — 147 citations
- Calibration of Confidence Measures in Speech Recognition (2011) — 82 citations
- WavLM: Large-Scale Self-Supervised Pre-Training for Full Stack Speech Processing (2021) — 3,371 citations
- Rapid adaptation for deep neural networks through multi-task learning (2015) — 69 citations
- SpeechT5: Unified-Modal Encoder-Decoder Pre-Training for Spoken Language Processing (2021) — 297 citations
- Unispeech-Sat: Universal Speech Representation Learning With Speaker Aware Pre-Training (2021) — 138 citations
- Speaker-Invariant Training Via Adversarial Learning (2018) — 115 citations
- Small-footprint high-performance deep neural network-based speech recognition using split-VQ (2015) — 41 citations
- Investigations on hessian-free optimization for cross-entropy training of deep neural networks (2013) — 33 citations
- Deep Convolutional Neural Networks with Layer-Wise Context Expansion and Attention (2016) — 80 citations
- Speak Foreign Languages with Your Own Voice: Cross-Lingual Neural Codec Language Modeling (2023) — 275 citations
- Low-rank plus diagonal adaptation for deep neural networks (2016) — 71 citations
- Recent progresses in deep learning based acoustic models (2017) — 166 citations
- Neural Codec Language Models are Zero-Shot Text to Speech Synthesizers (2023) — 1,289 citations