← Authors

W. Ronny Huang

15 papers · 2018–2023 · 5 conferences · across top CS/AI conferences

Achievements

πŸŒ‰ Interdisciplinary Bridge πŸƒ Academic Marathon (5) 🌈 Renaissance Researcher (5) 🐝 Cross-Pollinator (12) πŸ—ΊοΈ Taxonomy Completionist (28) 🌍 Conference Polyglot (5) 🧭 Keyword Pioneer 🐣 Hot Topic Early Bird πŸ† Keyword Champion πŸ—ƒοΈ Keyword Collector (59) ⚑ Prolific Year (5) πŸš€ Conference Pioneer πŸ“ˆ Trend Setter πŸ’Ž Century Club (15) πŸ”₯ Unstoppable (6) ❓ The Questioner

Conferences

INTERSPEECH (7) NIPS (3) ICLR (2) ICML (2) WACV (1)

Top co-authors

Tom Goldstein (7) Tara Sainath (5) Cal Peyser (5) Christoph Studer (3) Gavin Taylor (3) Shankar Kumar (3) David Rybach (3) Shuo-Yiin Chang (2) Jonas Geiping (2) Trevor Strohman (2)

Research topics

Privacy (1)

Keywords

language model (3) speech recognition (3) word error rate (3) adversarial attack (3) automatic speech recognition (3) data poisoning (2) clean-label poisoning (2) stochastic gradient descent (2) domain adaptation (1) privacy preservation (1) transfer learning (1) semantic segmentation (1) neural network optimization (1) feature space (1) convolutional neural network (1) batch normalization (1) bilevel optimization (1) knowledge distillation (1) artifact detection (1) discriminative training (1)

Papers

Semantic Segmentation with Bidirectional Language Models Improves Long-form ASR INTERSPEECH 2023
Detecting Unintended Memorization in Language-Model-Fused ASR INTERSPEECH 2022
Towards Disentangled Speech Representations INTERSPEECH 2022
Improving Rare Word Recognition with LM-aware MWER Training INTERSPEECH 2022
E2E Segmenter: Joint Segmenting and Decoding for Long-Form ASR INTERSPEECH 2022
Sentence-Select: Large-Scale Language Model Data Selection for Rare-Word Speech Recognition INTERSPEECH 2022
GradInit: Learning to Initialize Neural Networks for Stable and Efficient Training NIPS 2021
Witches' Brew: Industrial Scale Data Poisoning via Gradient Matching ICLR 2021
Lookup-Table Recurrent Language Models for Long Tail Speech Recognition INTERSPEECH 2021
DeepErase: Weakly Supervised Ink Artifact Removal in Document Text Images WACV 2020
MetaPoison: Practical General-purpose Clean-label Data Poisoning NIPS 2020
The Impact of Neural Network Overparameterization on Gradient Confusion and Stochastic Gradient Descent ICML 2020
Transferable Clean-Label Poisoning Attacks on Deep Neural Nets ICML 2019
Are adversarial examples inevitable? ICLR 2019
Poison Frogs! Targeted Clean-Label Poisoning Attacks on Neural Networks NIPS 2018