Rohit Prabhavalkar
Artificial Intelligence · 2010–2023
A researcher in the Science corpus: 24 papers; trusts 919 researchers and is trusted by 229 researchers here, as inferred from the citation graph.
Subfields
- Artificial Intelligence — 625 citations into it; #2,162 of 36,961 by trust here, #1,901 by citations
- Signal Processing — 271 citations into it; #235 of 7,592 by trust here, #127 by citations
- Speech & Audio — 245 citations into it; #180 of 1,080 by trust here, #99 by citations
- Natural Language Processing — 229 citations into it; #1,948 of 5,725 by trust here, #800 by citations
- Model Architectures — 146 citations into it; #525 of 2,288 by trust here, #539 by citations
- Computer Vision and Pattern Recognition — 115 citations into it
- Optimization & Training — 49 citations into it
- Hardware and Architecture — 33 citations into it
Whom Rohit Prabhavalkar trusts overall
Their strongest outbound trust, strongest first, inferred from their citations.
- Alex Graves
- Geoffrey E. Hinton
- Yoshua Bengio
- Diederik P. Kingma
- Ilya Sutskever
- Sepp Hochreiter
- Dzmitry Bahdanau
- J. Urgen Schmidhuber
- Brian Kingsbury
- Oriol Vinyals
Who trusts Rohit Prabhavalkar overall
- Dong Yu
- Tara N. Sainath
- Jinyu Li
- Li Deng
- Yanzhang He
- Bo Li
- Chung-Cheng Chiu
- Kanishka Rao
- Yu Zhang
- Wei Han
Papers from Rohit Prabhavalkar's perspective
Ordered by how strongly the researchers Rohit Prabhavalkar 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
- State-of-the-Art Speech Recognition with Sequence-to-Sequence Models (2017) — 1,190 citations
- Lingvo: a Modular and Scalable Framework for Sequence-to-Sequence Modeling (2019) — 215 citations
- An Analysis of Incorporating an External Language Model into a Sequence-to-Sequence Model (2017) — 282 citations
- Backpropagation training for multilayer conditional random field based phone recognition (2010) — 43 citations
- A Comparison of Sequence-to-Sequence Models for Speech Recognition (2017) — 307 citations
- Streaming End-to-end Speech Recognition for Mobile Devices (2018) — 676 citations
- On the compression of recurrent neural networks with an application to LVCSR acoustic modeling for embedded speech recognition (2016) — 104 citations
- Exploring architectures, data and units for streaming end-to-end speech recognition with RNN-transducer (2017) — 365 citations
- Model Unit Exploration for Sequence-to-Sequence Speech Recognition (2019) — 37 citations
- Personalized speech recognition on mobile devices (2016) — 201 citations
- A Comparison of End-to-End Models for Long-Form Speech Recognition (2019) — 92 citations
- A Streaming On-Device End-To-End Model Surpassing Server-Side Conventional Model Quality and Latency (2020) — 228 citations
- Recognizing Long-Form Speech Using Streaming End-to-End Models (2019) — 137 citations
- RNN-T Models Fail to Generalize to Out-of-Domain Audio: Causes and Solutions (2020) — 44 citations
- Streaming small-footprint keyword spotting using sequence-to-sequence models (2017) — 96 citations
- Automatic gain control and multi-style training for robust small-footprint keyword spotting with deep neural networks (2015) — 93 citations
- Two-Pass End-to-End Speech Recognition (2019) — 163 citations
- Less is More: Improved RNN-T Decoding Using Limited Label Context and Path Merging (2020) — 37 citations
- An Analysis of "Attention" in Sequence-to-Sequence Models (2017) — 45 citations
- Google USM: Scaling Automatic Speech Recognition Beyond 100 Languages (2023) — 396 citations