Hank Liao

Artificial Intelligence · 2013–2019

A researcher in the Science corpus: 6 papers; trusts 60 researchers and is trusted by 129 researchers here, as inferred from the citation graph.

Subfields

• Artificial Intelligence — 73 citations into it; #1,598 of 35,345 by trust here, #5,424 by citations
• Signal Processing — 54 citations into it; #162 of 7,572 by trust here, #563 by citations
• Natural Language Processing — 38 citations into it
• Speech & Audio — 28 citations into it; #152 of 1,076 by trust here, #299 by citations
• Model Architectures — 23 citations into it
• Computer Vision and Pattern Recognition — 19 citations into it
• Optimization & Training — 8 citations into it

Whom Hank Liao trusts overall

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

1. Geoffrey E. Hinton
2. Abdel-rahman Mohamed
3. Hynek Hermansky
4. Mark John Francis Gales
5. Navdeep Jaitly
6. Alex Graves
7. Frank Torsten Bernd Seide
8. Dong Yu
9. Volodymyr Mnih
10. Andrew W. Senior

Who trusts Hank Liao overall

1. Dong Yu
2. Jinyu Li
3. Li Deng
4. Mary Harper
5. Kyu J. Han
6. Yajie Miao
7. Zhong Meng
8. Bo Li
9. Arun Narayanan
10. Tara N. Sainath

Papers from Hank Liao's perspective

Ordered by how strongly the researchers Hank Liao trusts endorse each paper. Same corpus, a different order for every researcher.

1. ImageNet classification with deep convolutional neural networks
2. Deep Residual Learning for Image Recognition (Computer Vision and Pattern Recognition)
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. Very Deep Convolutional Networks for Large-Scale Image Recognition (International Conference on Learning Representations)
8. ImageNet: A large-scale hierarchical image database
9. Neural Machine Translation by Jointly Learning to Align and Translate (International Conference on Learning Representations)
10. Sequence to Sequence Learning with Neural Networks (Neural Information Processing Systems)

Their papers

• Large scale deep neural network acoustic modeling with semi-supervised training data for YouTube video transcription (2013) — 216 citations
• Neural Speech Recognizer: Acoustic-to-Word LSTM Model for Large Vocabulary Speech Recognition (2016) — 317 citations
• Large-Scale Visual Speech Recognition (2018) — 172 citations
• Speaker adaptation of context dependent deep neural networks (2013) — 245 citations
• A Comparison of End-to-End Models for Long-Form Speech Recognition (2019) — 92 citations
• Lattice rescoring strategies for long short term memory language models in speech recognition (2017) — 41 citations