Vimal Manohar

Artificial Intelligence · 2015–2023

A researcher in the Science corpus: 12 papers; trusts 131 researchers and is trusted by 52 researchers here, as inferred from the citation graph.

Subfields

• Artificial Intelligence — 211 citations into it; #4,381 of 35,345 by trust here, #4,276 by citations
• Signal Processing — 156 citations into it; #773 of 7,572 by trust here, #476 by citations
• Speech & Audio — 156 citations into it; #175 of 1,076 by trust here, #161 by citations
• Natural Language Processing — 52 citations into it
• Computer Vision and Pattern Recognition — 35 citations into it
• Model Architectures — 33 citations into it; #1,610 of 2,278 by trust here, #1,548 by citations
• Evaluation & Benchmarks — 25 citations into it
• Representation & Self-Supervised Learning — 20 citations into it; #1,519 of 3,145 by trust here, #2,178 by citations

Whom Vimal Manohar trusts overall

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

1. Daniel Povey
2. Florin Curelaru
3. Geoffrey E. Hinton
4. Vijayaditya Peddinti
5. Sanjeev Khudanpur
6. Karel Veselý
7. Sergey Ioffe
8. Yoshua Bengio
9. Alex Graves
10. Pegah Ghahremani

Who trusts Vimal Manohar overall

1. Daniel Povey
2. Vijayaditya Peddinti
3. Sanjeev Khudanpur
4. Hossein Hadian
5. Kritika Singh
6. Shinji Watanabe
7. Tatiana Likhomanenko
8. Alexei Baevski
9. Karel Veselý
10. Thomas Drugman

Papers from Vimal Manohar's perspective

Ordered by how strongly the researchers Vimal Manohar 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. Adam: A Method for Stochastic Optimization (International Conference on Learning Representations)
3. ImageNet classification with deep convolutional neural networks
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. Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift (International Conference on Machine Learning)
9. Very Deep Convolutional Networks for Large-Scale Image Recognition (International Conference on Learning Representations)
10. Neural Machine Translation by Jointly Learning to Align and Translate (International Conference on Learning Representations)

Their papers

• Purely Sequence-Trained Neural Networks for ASR Based on Lattice-Free MMI (2016) — 891 citations
• Semi-supervised maximum mutual information training of deep neural network acoustic models (2015) — 49 citations
• Investigation of transfer learning for ASR using LF-MMI trained neural networks (2017) — 75 citations
• Semi-Supervised Training of Acoustic Models Using Lattice-Free MMI (2018) — 83 citations
• JHU ASpIRE system: Robust LVCSR with TDNNS, iVector adaptation and RNN-LMS (2015) — 115 citations
• Acoustic Modelling from the Signal Domain Using CNNs (2016) — 92 citations
• JHU Kaldi system for Arabic MGB-3 ASR challenge using diarization, audio-transcript alignment and transfer learning (2017) — 53 citations
• Large scale weakly and semi-supervised learning for low-resource video ASR (2020) — 10 citations
• Diarization is Hard: Some Experiences and Lessons Learned for the JHU Team in the Inaugural DIHARD Challenge (2018) — 234 citations
• Voicebox: Text-Guided Multilingual Universal Speech Generation at Scale (2023) — 551 citations
• Far-Field ASR Without Parallel Data (2016) — 48 citations
• Acoustic Modeling for Overlapping Speech Recognition: Jhu Chime-5 Challenge System (2019) — 21 citations