Lei He

Artificial Intelligence · with Liu · 2015–2023

A researcher in the Science corpus: 29 papers; trusts 567 researchers and is trusted by 61 researchers here, as inferred from the citation graph.

Subfields

• Artificial Intelligence — 601 citations into it; #3,689 of 35,345 by trust here, #2,817 by citations
• Speech & Audio — 384 citations into it; #771 of 1,076 by trust here, #235 by citations
• Signal Processing — 383 citations into it; #1,819 of 7,572 by trust here, #656 by citations
• Generative Models — 176 citations into it
• Computer Vision and Pattern Recognition — 155 citations into it
• Natural Language Processing — 155 citations into it
• Model Architectures — 95 citations into it
• Representation & Self-Supervised Learning — 40 citations into it

Whom Lei He trusts overall

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

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

Who trusts Lei He overall

1. Xu Tan
2. Tao Qin
3. Frank K. Soong
4. Zhaoxi Mu
5. Rui Liu
6. J. Yang
7. Tie-Yan Liu
8. Cong Han
9. Feiyu Shen
10. Yixuan Zhou

Papers from Lei He's perspective

Ordered by how strongly the researchers Lei He 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. Sequence to Sequence Learning with Neural Networks (Neural Information Processing Systems)
10. Neural Machine Translation by Jointly Learning to Align and Translate (International Conference on Learning Representations)

Their papers

• Speak Foreign Languages with Your Own Voice: Cross-Lingual Neural Codec Language Modeling (2023) — 275 citations
• Infergrad: Improving Diffusion Models for Vocoder by Considering Inference in Training (2022) — 37 citations
• Neural Codec Language Models are Zero-Shot Text to Speech Synthesizers (2023) — 1,289 citations
• Learning Latent Representations for Style Control and Transfer in End-to-end Speech Synthesis (2018) — 249 citations
• Robust Sequence-to-Sequence Acoustic Modeling with Stepwise Monotonic Attention for Neural TTS (2019) — 84 citations
• A New GAN-based End-to-End TTS Training Algorithm (2019) — 49 citations
• NaturalSpeech 2: Latent Diffusion Models are Natural and Zero-Shot Speech and Singing Synthesizers (2023) — 394 citations
• Improving Prosody with Linguistic and Bert Derived Features in Multi-Speaker Based Mandarin Chinese Neural TTS (2020) — 52 citations
• AdaSpeech 4: Adaptive Text to Speech in Zero-Shot Scenarios (2022) — 78 citations
• FoundationTTS: Text-to-Speech for ASR Customization with Generative Language Model (2023) — 9 citations
• AUDIT: Audio Editing by Following Instructions with Latent Diffusion Models (2023) — 107 citations
• PromptTTS 2: Describing and Generating Voices with Text Prompt (2023) — 87 citations
• Cross-Lingual Text-to-Speech Using Multi-Task Learning and Speaker Classifier Joint Training (2022) — 12 citations
• NaturalSpeech: End-to-End Text-to-Speech Synthesis With Human-Level Quality (2022) — 351 citations
• Self-supervised Context-aware Style Representation for Expressive Speech Synthesis (2022) — 17 citations
• DelightfulTTS 2: End-to-End Speech Synthesis with Adversarial Vector-Quantized Auto-Encoders (2022) — 35 citations
• Joint Pre-Training with Speech and Bilingual Text for Direct Speech to Speech Translation (2022) — 18 citations
• DelightfulTTS: The Microsoft Speech Synthesis System for Blizzard Challenge 2021 (2021) — 63 citations
• Multilingual Byte2Speech Text-To-Speech Models Are Few-shot Spoken Language Learners (2021)
• Exploring Machine Speech Chain for Domain Adaptation and Few-Shot Speaker Adaptation (2021) — 9 citations