Heiga Zen
Artificial Intelligence · 2002–2025
A researcher in the Science corpus: 42 papers; trusts 1,088 researchers and is trusted by 1,862 researchers here, as inferred from the citation graph.
Subfields
- Artificial Intelligence — 778 citations into it; #1,185 of 36,961 by trust here, #653 by citations
- Signal Processing — 362 citations into it; #23 of 7,592 by trust here, #11 by citations
- Speech & Audio — 344 citations into it; #3 of 1,080 by trust here, #1 by citations
- Natural Language Processing — 237 citations into it; #2,113 of 5,725 by trust here, #617 by citations
- Computer Vision and Pattern Recognition — 163 citations into it; #1,511 of 21,973 by trust here, #587 by citations
- Generative Models — 139 citations into it; #152 of 1,963 by trust here, #45 by citations
- Model Architectures — 93 citations into it; #1,623 of 2,288 by trust here, #939 by citations
- Experimental and Cognitive Psychology — 72 citations into it; #6,124 of 9,929 by trust here, #8,195 by citations
Whom Heiga Zen trusts overall
Their strongest outbound trust, strongest first, inferred from their citations.
- Keiichi Tokuda
- Satoshi Imai
- Geoffrey E. Hinton
- Tomoki Toda
- Yoshua Bengio
- Diederik P. Kingma
- Alex Graves
- Alan W. Black
- Sargur N. Srihari
- Mike Schuster
Who trusts Heiga Zen overall
- Xu Tan
- Chenpeng Du
- Zhizheng Wu
- Keiichi Tokuda
- Junichi Yamagishi
- Li Deng
- Yannis Agiomyrgiannakis
- Ye Jia
- Frank K. Soong
- Tao Qin
Papers from Heiga Zen's perspective
Ordered by how strongly the researchers Heiga Zen 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
- Sequence to Sequence Learning with Neural Networks (Neural Information Processing Systems)
- 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)
Their papers
- WaveNet: A Generative Model for Raw Audio (2016) — 8,319 citations
- Parallel WaveNet: Fast High-Fidelity Speech Synthesis (2017) — 912 citations
- WaveGrad: Estimating Gradients for Waveform Generation (2020) — 957 citations
- Lingvo: a Modular and Scalable Framework for Sequence-to-Sequence Modeling (2019) — 215 citations
- Sample Efficient Adaptive Text-to-Speech (2018) — 162 citations
- Hierarchical Generative Modeling for Controllable Speech Synthesis (2018) — 295 citations
- Fast, Compact, and High Quality LSTM-RNN Based Statistical Parametric Speech Synthesizers for Mobile Devices (2016) — 122 citations
- Statistical parametric speech synthesis using deep neural networks (2013) — 924 citations
- Reformulating the HMM as a trajectory model by imposing explicit relationships between static and dynamic feature vector sequences (2004) — 187 citations
- MAESTRO: Matched Speech Text Representations through Modality Matching (2022) — 125 citations
- Directly modeling voiced and unvoiced components in speech waveforms by neural networks (2016) — 33 citations
- Statistical Parametric Speech Synthesis (2007) — 1,584 citations
- Statistical parametric speech synthesis with joint estimation of acoustic and excitation model parameters (2010) — 22 citations
- WaveGrad 2: Iterative Refinement for Text-to-Speech Synthesis (2021) — 102 citations
- Deep mixture density networks for acoustic modeling in statistical parametric speech synthesis (2014) — 235 citations
- CVSS Corpus and Massively Multilingual Speech-to-Speech Translation (2022) — 102 citations
- Product of Experts for Statistical Parametric Speech Synthesis (2012) — 56 citations
- Semi-Supervision in ASR: Sequential MixMatch and Factorized TTS-Based Augmentation (2021) — 17 citations
- LibriTTS: A Corpus Derived from LibriSpeech for Text-to-Speech (2019) — 1,387 citations
- Autoregressive Models for Statistical Parametric Speech Synthesis (2013) — 68 citations