Daniel Povey
Artificial Intelligence · 2002–2023
A researcher in the Science corpus: 48 papers; trusts 712 researchers and is trusted by 5,562 researchers here, as inferred from the citation graph.
Subfields
- Artificial Intelligence — 471 citations into it; #242 of 36,961 by trust here, #339 by citations
- Signal Processing — 239 citations into it; #11 of 7,592 by trust here, #18 by citations
- Speech & Audio — 234 citations into it; #8 of 1,080 by trust here, #19 by citations
- Natural Language Processing — 142 citations into it; #5,598 of 5,725 by trust here, #4,141 by citations
- Model Architectures — 60 citations into it; #210 of 2,288 by trust here, #369 by citations
- Computer Vision and Pattern Recognition — 48 citations into it; #4,118 of 21,973 by trust here, #9,347 by citations
- Optimization & Training — 44 citations into it; #323 of 2,605 by trust here, #427 by citations
- Evaluation & Benchmarks — 42 citations into it; #110 of 3,155 by trust here, #202 by citations
Whom Daniel Povey trusts overall
Their strongest outbound trust, strongest first, inferred from their citations.
- Geoffrey E. Hinton
- Yoshua Bengio
- Vijayaditya Peddinti
- Alex Graves
- Sanjeev Khudanpur
- Shun-ichi Amari
- Philip C. Woodland
- Yann LeCun
- Ilya Sutskever
- Sergey Ioffe
Who trusts Daniel Povey overall
- Vimal Manohar
- Li Deng
- Shinji Watanabe
- Dong Yu
- Sanjeev Khudanpur
- Vijayaditya Peddinti
- Yoshua Bengio
- Mirco Ravanelli
- David Snyder
- Yu Zhang
Papers from Daniel Povey's perspective
Ordered by how strongly the researchers Daniel Povey 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)
- Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift (International Conference on Machine Learning)
- Neural Machine Translation by Jointly Learning to Align and Translate (International Conference on Learning Representations)
Their papers
- The Kaldi Speech Recognition Toolkit (2011) — 6,607 citations
- Librispeech: An ASR corpus based on public domain audio books (2015) — 8,192 citations
- Strategies for training large scale neural network language models (2011) — 567 citations
- Sequence-discriminative training of deep neural networks (2013) — 765 citations
- Minimum Phone Error and I-smoothing for improved discriminative training (2002) — 811 citations
- Audio augmentation for speech recognition (2015) — 1,266 citations
- Krylov Subspace Descent for Deep Learning (2011) — 154 citations
- Boosted MMI for model and feature-space discriminative training (2008) — 438 citations
- Multilingual acoustic modeling for speech recognition based on subspace Gaussian Mixture Models (2010) — 196 citations
- Revisiting Recurrent Neural Networks for robust ASR (2012) — 169 citations
- Purely Sequence-Trained Neural Networks for ASR Based on Lattice-Free MMI (2016) — 891 citations
- Improving deep neural network acoustic models using generalized maxout networks (2014) — 315 citations
- A time delay neural network architecture for efficient modeling of long temporal contexts (2015) — 1,083 citations
- X-Vectors: Robust DNN Embeddings for Speaker Recognition (2018) — 3,060 citations
- A Time-Restricted Self-Attention Layer for ASR (2018) — 163 citations
- fMPE: discriminatively trained features for speech recognition (2005) — 331 citations
- Semi-supervised maximum mutual information training of deep neural network acoustic models (2015) — 49 citations
- Parallel training of Deep Neural Networks with Natural Gradient and Parameter Averaging (2014) — 250 citations
- MUSAN: A Music, Speech, and Noise Corpus (2015) — 1,702 citations
- Large scale discriminative training of hidden Markov models for speech recognition (2002) — 369 citations