Shinji Watanabe
Artificial Intelligence · 2011–2023
A researcher in the Science corpus: 70 papers; trusts 2,163 researchers and is trusted by 735 researchers here, as inferred from the citation graph.
Subfields
- Artificial Intelligence — 1,621 citations into it; #1,196 of 36,961 by trust here, #808 by citations
- Signal Processing — 950 citations into it; #44 of 7,592 by trust here, #34 by citations
- Speech & Audio — 793 citations into it; #16 of 1,080 by trust here, #23 by citations
- Natural Language Processing — 511 citations into it; #3,234 of 5,725 by trust here, #2,750 by citations
- Computer Vision and Pattern Recognition — 345 citations into it; #9,127 of 21,973 by trust here, #9,347 by citations
- Model Architectures — 272 citations into it; #1,618 of 2,288 by trust here, #793 by citations
- Representation & Self-Supervised Learning — 152 citations into it; #2,900 of 3,156 by trust here, #2,185 by citations
- Evaluation & Benchmarks — 145 citations into it; #709 of 3,155 by trust here, #612 by citations
Whom Shinji Watanabe trusts overall
Their strongest outbound trust, strongest first, inferred from their citations.
- Alex Graves
- Geoffrey E. Hinton
- Yoshua Bengio
- Dzmitry Bahdanau
- Diederik P. Kingma
- Ilya Sutskever
- Daniel Povey
- Alex Krizhevsky
- Jan Chorowski
- Sepp Hochreiter
Who trusts Shinji Watanabe overall
- Jinyu Li
- Takaaki Hori
- Dong Yu
- Mirco Ravanelli
- Zhuo Chen
- Tomoki Hayashi
- John R. Hershey
- Jonathan Le Roux
- Murali Karthick Baskar
- Yi Luo
Papers from Shinji Watanabe's perspective
Ordered by how strongly the researchers Shinji Watanabe 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)
- Long Short-Term Memory
- Attention is All you Need (Neural Information Processing Systems)
- Gradient-based learning applied to document recognition
- ImageNet: A large-scale hierarchical image database
- Very Deep Convolutional Networks for Large-Scale Image Recognition (International Conference on Learning Representations)
- Neural Machine Translation by Jointly Learning to Align and Translate (International Conference on Learning Representations)
- Sequence to Sequence Learning with Neural Networks (Neural Information Processing Systems)
Their papers
- Deep clustering: Discriminative embeddings for segmentation and separation (2015) — 1,455 citations
- ESPnet: End-to-End Speech Processing Toolkit (2018) — 1,730 citations
- A Comparative Study on Transformer vs RNN in Speech Applications (2019) — 796 citations
- The third ‘CHiME’ speech separation and recognition challenge: Dataset, task and baselines (2015) — 423 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
- Transfer Learning of Language-independent End-to-end ASR with Language Model Fusion (2018) — 46 citations
- GigaSpeech: An Evolving, Multi-domain ASR Corpus with 10, 000 Hours of Transcribed Audio (2021) — 607 citations
- Cycle-consistency Training for End-to-end Speech Recognition (2018) — 90 citations
- Joint CTC-attention based end-to-end speech recognition using multi-task learning (2016) — 1,000 citations
- Multilingual Sequence-to-Sequence Speech Recognition: Architecture, Transfer Learning, and Language Modeling (2018) — 130 citations
- Multi-Modal Data Augmentation for End-to-end ASR (2018) — 40 citations
- CHiME-6 Challenge: Tackling Multispeaker Speech Recognition for Unsegmented Recordings (2020) — 407 citations
- Self-supervised Sequence-to-sequence ASR using Unpaired Speech and Text (2019) — 37 citations
- Speech Enhancement with LSTM Recurrent Neural Networks and its Application to Noise-Robust ASR (2015) — 650 citations
- Recurrent deep neural networks for robust speech recognition (2014) — 139 citations
- The fifth 'CHiME' Speech Separation and Recognition Challenge: Dataset, task and baselines (2018) — 729 citations
- Advances in Joint CTC-Attention Based End-to-End Speech Recognition with a Deep CNN Encoder and RNN-LM (2017) — 310 citations
- Massively Multilingual Adversarial Speech Recognition (2019) — 83 citations
- Speech enhancement and recognition using multi-task learning of long short-term memory recurrent neural networks (2015) — 157 citations