Tomoki Hayashi
Artificial Intelligence · 2017–2021
A researcher in the Science corpus: 16 papers; trusts 680 researchers and is trusted by 73 researchers here, as inferred from the citation graph.
Subfields
- Artificial Intelligence — 413 citations into it; #3,828 of 36,961 by trust here, #2,791 by citations
- Signal Processing — 209 citations into it; #574 of 7,592 by trust here, #278 by citations
- Speech & Audio — 200 citations into it; #150 of 1,080 by trust here, #114 by citations
- Natural Language Processing — 167 citations into it
- Computer Vision and Pattern Recognition — 98 citations into it
- Model Architectures — 77 citations into it; #1,503 of 2,288 by trust here, #919 by citations
- Evaluation & Benchmarks — 29 citations into it
- Generative Models — 29 citations into it
Whom Tomoki Hayashi trusts overall
Their strongest outbound trust, strongest first, inferred from their citations.
- Diederik P. Kingma
- Alex Graves
- Geoffrey E. Hinton
- Yoshua Bengio
- Dzmitry Bahdanau
- Ilya Sutskever
- Jimmy Ba
- Aäron van den Oord
- Alex Krizhevsky
- Kyunghyun Cho
Who trusts Tomoki Hayashi overall
- Junichi Yamagishi
- Ryuichi Yamamoto
- Hieu-Thi Luong
- Takuma Okamoto
- Shinji Watanabe
- Eunwoo Song
- Berrak Sisman
- Yang Ai
- Xin Eric Wang
- Tomoki Toda
Papers from Tomoki Hayashi's perspective
Ordered by how strongly the researchers Tomoki Hayashi trusts endorse each paper. Same corpus, a different order for every researcher.
- Deep Residual Learning for Image Recognition (Computer Vision and Pattern Recognition)
- ImageNet classification with deep convolutional neural networks
- Adam: A Method for Stochastic Optimization (International Conference on Learning Representations)
- Attention is All you Need (Neural Information Processing Systems)
- Long Short-Term Memory
- Gradient-based learning applied to document recognition
- ImageNet: A large-scale hierarchical image database
- Sequence to Sequence Learning with Neural Networks (Neural Information Processing Systems)
- Neural Machine Translation by Jointly Learning to Align and Translate (International Conference on Learning Representations)
- Very Deep Convolutional Networks for Large-Scale Image Recognition (International Conference on Learning Representations)
Their papers
- ESPnet: End-to-End Speech Processing Toolkit (2018) — 1,730 citations
- A Comparative Study on Transformer vs RNN in Speech Applications (2019) — 796 citations
- Back-Translation-Style Data Augmentation for end-to-end ASR (2018) — 109 citations
- Hybrid CTC/Attention Architecture for End-to-End Speech Recognition (2017) — 882 citations
- Cycle-consistency Training for End-to-end Speech Recognition (2018) — 90 citations
- Recent Developments on Espnet Toolkit Boosted By Conformer (2020) — 292 citations
- ESPnet-ST: All-in-One Speech Translation Toolkit (2020) — 174 citations
- Espnet-TTS: Unified, Reproducible, and Integratable Open Source End-to-End Text-to-Speech Toolkit (2019) — 233 citations
- Speaker-Dependent WaveNet Vocoder (2017) — 267 citations
- Pre-Trained Text Embeddings for Enhanced Text-to-Speech Synthesis (2019) — 76 citations
- Discretization and Re-synthesis: an alternative method to solve the Cocktail Party Problem (2021) — 22 citations
- Quasi-Periodic Parallel WaveGAN Vocoder: A Non-autoregressive Pitch-dependent Dilated Convolution Model for Parametric Speech Generation (2020) — 4 citations
- Pretraining Techniques for Sequence-to-Sequence Voice Conversion (2020) — 49 citations
- Cyclic Spectral Modeling for Unsupervised Unit Discovery into Voice Conversion with Excitation and Waveform Modeling (2020) — 8 citations
- Semi-Supervised Speaker Adaptation for End-to-End Speech Synthesis with Pretrained Models (2020) — 14 citations
- An investigation of multi-speaker training for wavenet vocoder (2017) — 100 citations