Cheng-I Lai

Artificial Intelligence · 2019–2022

A researcher in the Science corpus: 8 papers; trusts 159 researchers and is trusted by 5 researchers here, as inferred from the citation graph.

Subfields

• Artificial Intelligence — 166 citations into it; #19,401 of 35,345 by trust here, #7,346 by citations
• Signal Processing — 113 citations into it; #6,091 of 7,572 by trust here, #1,783 by citations
• Speech & Audio — 89 citations into it; #1,000 of 1,076 by trust here, #390 by citations
• Natural Language Processing — 46 citations into it
• Representation & Self-Supervised Learning — 46 citations into it
• Computer Vision and Pattern Recognition — 44 citations into it
• Model Architectures — 19 citations into it
• Large Language Models — 18 citations into it; #460 of 799 by trust here, #770 by citations

Whom Cheng-I Lai trusts overall

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

1. Diederik P. Kingma
2. Geoffrey E. Hinton
3. Yoshua Bengio
4. Alex Krizhevsky
5. Kaiming He
6. Ilya Sutskever
7. Alex Graves
8. Yann LeCun
9. Oriol Vinyals
10. Andrew Zisserman

Who trusts Cheng-I Lai overall

1. Lasse Borgholt
2. Erica Cooper
3. Eyal Ben-David
4. Edresson Casanova
5. Puyuan Peng
6. Junichi Yamagishi
7. Xu Tan
8. Hieu-Thi Luong
9. Shu-Wen Yang
10. Zexin Cai

Papers from Cheng-I Lai's perspective

Ordered by how strongly the researchers Cheng-I Lai 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. Attention is All you Need (Neural Information Processing Systems)
5. Long Short-Term Memory
6. ImageNet: A large-scale hierarchical image database
7. Gradient-based learning applied to document recognition
8. Very Deep Convolutional Networks for Large-Scale Image Recognition (International Conference on Learning Representations)
9. Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift (International Conference on Machine Learning)
10. BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding (North American Chapter of the Association for Computational Linguistics)

Their papers

• SSAST: Self-Supervised Audio Spectrogram Transformer (2021) — 416 citations
• SUPERB: Speech processing Universal PERformance Benchmark (2021) — 1,225 citations
• Semi-Supervised Spoken Language Understanding via Self-Supervised Speech and Language Model Pretraining (2020) — 65 citations
• Zero-Shot Multi-Speaker Text-To-Speech with State-Of-The-Art Neural Speaker Embeddings (2019) — 204 citations
• SUPERB-SG: Enhanced Speech processing Universal PERformance Benchmark for Semantic and Generative Capabilities (2022) — 133 citations
• Conditioned Natural Language Generation using only Unconditioned Language Model: An Exploration (2020) — 18 citations
• Improved Prosody from Learned F0 Codebook Representations for VQ-VAE Speech Waveform Reconstruction (2020) — 21 citations
• Can Speaker Augmentation Improve Multi-Speaker End-to-End TTS? (2020) — 25 citations