Lei Xie

Artificial Intelligence · with Yang · 2013–2022

A researcher in the Science corpus: 31 papers; trusts 579 researchers and is trusted by 48 researchers here, as inferred from the citation graph.

Subfields

• Artificial Intelligence — 523 citations into it; #4,426 of 35,345 by trust here, #3,895 by citations
• Signal Processing — 381 citations into it; #690 of 7,572 by trust here, #382 by citations
• Speech & Audio — 280 citations into it; #472 of 1,076 by trust here, #528 by citations
• Natural Language Processing — 169 citations into it
• Computer Vision and Pattern Recognition — 119 citations into it
• Generative Models — 97 citations into it
• Model Architectures — 74 citations into it
• Representation & Self-Supervised Learning — 39 citations into it

Whom Lei Xie trusts overall

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

1. Geoffrey E. Hinton
2. Alex Graves
3. Diederik P. Kingma
4. Yoshua Bengio
5. Ilya Sutskever
6. Alex Krizhevsky
7. Yann LeCun
8. Radford M. Neal
9. J. Urgen Schmidhuber
10. Kaiming He

Who trusts Lei Xie overall

1. Xu Tan
2. Tao Qin
3. Frank K. Soong
4. Zhaoxi Mu
5. Maarten Versteegh
6. Tie-Yan Liu
7. Rui Liu
8. Kyubyong Park
9. Xiaochun An
10. Zhong Meng

Papers from Lei Xie's perspective

Ordered by how strongly the researchers Lei Xie 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. Long Short-Term Memory
5. Attention is All you Need (Neural Information Processing Systems)
6. Gradient-based learning applied to document recognition
7. ImageNet: A large-scale hierarchical image database
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. Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift (International Conference on Machine Learning)

Their papers

• Multi-Band Melgan: Faster Waveform Generation For High-Quality Text-To-Speech (2020) — 238 citations
• Context-dependent deep neural networks for commercial Mandarin speech recognition applications (2013) — 4 citations
• Extracting bottleneck features and word-like pairs from untranscribed speech for feature representation (2017) — 20 citations
• WeNet: Production Oriented Streaming and Non-Streaming End-to-End Speech Recognition Toolkit (2021) — 327 citations
• Multilingual bottle-neck feature learning from untranscribed speech (2017) — 31 citations
• An unsupervised deep domain adaptation approach for robust speech recognition (2017) — 164 citations
• A New GAN-based End-to-End TTS Training Algorithm (2019) — 49 citations
• Sequence to Multi-Sequence Learning via Conditional Chain Mapping for Mixture Signals (2020) — 27 citations
• DCCRN: Deep Complex Convolution Recurrent Network for Phase-Aware Speech Enhancement (2020) — 804 citations
• Parallel inference of dirichlet process Gaussian mixture models for unsupervised acoustic modeling: a feasibility study (2015) — 76 citations
• Investigating Generative Adversarial Networks based Speech Dereverberation for Robust Speech Recognition (2018) — 40 citations
• Opencpop: A High-Quality Open Source Chinese Popular Song Corpus for Singing Voice Synthesis (2022) — 147 citations
• AISHELL-4: An Open Source Dataset for Speech Enhancement, Separation, Recognition and Speaker Diarization in Conference Scenario (2021) — 162 citations
• Improving Performance of Seen and Unseen Speech Style Transfer in End-to-end Neural TTS (2021) — 11 citations
• Glow-WaveGAN: Learning Speech Representations from GAN-based Variational Auto-Encoder For High Fidelity Flow-based Speech Synthesis (2021) — 29 citations
• The Multi-Speaker Multi-Style Voice Cloning Challenge 2021 (2021) — 29 citations
• WENETSPEECH: A 10000+ Hours Multi-Domain Mandarin Corpus for Speech Recognition (2021) — 361 citations
• Cycle consistent network for end-to-end style transfer TTS training (2021) — 27 citations
• Data Efficient Voice Cloning from Noisy Samples with Domain Adversarial Training (2020) — 33 citations
• Fine-Grained Emotion Strength Transfer, Control and Prediction for Emotional Speech Synthesis (2020) — 66 citations