Lin-Shan Lee

Artificial Intelligence · 2013–2019

A researcher in the Science corpus: 11 papers; trusts 296 researchers and is trusted by 45 researchers here, as inferred from the citation graph.

Subfields

• Artificial Intelligence — 195 citations into it; #5,156 of 35,345 by trust here, #6,720 by citations
• Signal Processing — 87 citations into it; #907 of 7,572 by trust here, #880 by citations
• Natural Language Processing — 85 citations into it
• Speech & Audio — 81 citations into it; #196 of 1,076 by trust here, #308 by citations
• Computer Vision and Pattern Recognition — 53 citations into it
• Representation & Self-Supervised Learning — 48 citations into it; #1,100 of 3,145 by trust here, #1,561 by citations
• Model Architectures — 30 citations into it
• Generative Models — 24 citations into it

Whom Lin-Shan Lee trusts overall

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

1. Yoshua Bengio
2. Geoffrey E. Hinton
3. Alex Graves
4. Ilya Sutskever
5. Aren Jansen
6. Tomas Mikolov
7. Diederik P. Kingma
8. Alex Krizhevsky
9. James R. Glass
10. J. Urgen Schmidhuber

Who trusts Lin-Shan Lee overall

1. Hung-yi Lee
2. Herman Kamper
3. Yi-Chen Chen
4. Alexei Baevski
5. Marcely Zanon Boito
6. Wei-Ning Hsu
7. Yu-An Chung
8. Abdel-rahman Mohamed
9. Yung-Sung Chuang
10. Murali Karthick Baskar

Papers from Lin-Shan Lee's perspective

Ordered by how strongly the researchers Lin-Shan Lee 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. Sequence to Sequence Learning with Neural Networks (Neural Information Processing Systems)
9. Very Deep Convolutional Networks for Large-Scale Image Recognition (International Conference on Learning Representations)
10. BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding (North American Chapter of the Association for Computational Linguistics)

Their papers

• Completely Unsupervised Phoneme Recognition by Adversarially Learning Mapping Relationships from Audio Embeddings (2018) — 51 citations
• Adversarial Training of End-to-end Speech Recognition Using a Criticizing Language Model (2018) — 47 citations
• Audio Word2Vec: Unsupervised Learning of Audio Segment Representations Using Sequence-to-Sequence Autoencoder (2016) — 194 citations
• Segmental Audio Word2Vec: Representing Utterances as Sequences of Vectors with Applications in Spoken Term Detection (2018) — 55 citations
• Towards Unsupervised Speech Recognition and Synthesis with Quantized Speech Representation Learning (2019) — 53 citations
• Recurrent neural network based language model personalization by social network crowdsourcing (2013) — 38 citations
• SpeechBERT: An Audio-and-Text Jointly Learned Language Model for End-to-End Spoken Question Answering (2019) — 108 citations
• Completely Unsupervised Speech Recognition By A Generative Adversarial Network Harmonized With Iteratively Refined Hidden Markov Models (2019) — 19 citations
• Almost-unsupervised Speech Recognition with Close-to-zero Resource Based on Phonetic Structures Learned from Very Small Unpaired Speech and Text Data (2018) — 17 citations
• Multi-target Voice Conversion without Parallel Data by Adversarially Learning Disentangled Audio Representations (2018) — 137 citations
• Spoken Content Retrieval—Beyond Cascading Speech Recognition with Text Retrieval (2015) — 118 citations