Joseph Szurley

3 papers · 2018–2021 · 2 venues · across top CS/AI venues

Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.

Achievements

Jump to papers ↓

🌍 Conference Polyglot · Bronze 🌉 Interdisciplinary Bridge · Bronze 🗺️ Taxonomy Completionist (12) 🐣 Hot Topic Early Bird

Venues

Interspeech (2) NeurIPS (1)

Top co-authors

Florian Metze (2) Juncheng Li (2) J. Zico Kolter (1) Yun Wang (1) Jasha Droppo (1) Xinjian Li (1) Shuhui Qu (1) Muhammad A. Shah (1) Samarjit Das (1) Shao-Yen Tseng (1)

Research topics

Machine Learning (3) Speech & Audio (3) Deep Learning (2) Learning Types · Machine Learning (2) Learning Types · Deep Learning (2) Recognition (2) Artificial Intelligence (1) Analysis (1) Application Areas (1) Architectures (1) Core AI (1) Techniques (1)

Keywords

deep neural network (2) automatic speech recognition (1) multiple instance learning (1) adversarial attack (1) convolutional neural network (1) membership inference attack (1) audio embedding (1) small-footprint model (1) voice assistant (1) audio tagging (1) wake word detection (1) audio event detection (1) model vulnerability (1) audio adversarial attack (1) audio adversarial example (1) speaker privacy (1) weakly supervised learning (1) expectation over transform (1)

Papers

Evaluating the Vulnerability of End-to-End Automatic Speech Recognition Models to Membership Inference Attacks Interspeech 2021 Adversarial Music: Real world Audio Adversary against Wake-word Detection System NeurIPS 2019 Multiple Instance Deep Learning for Weakly Supervised Small-Footprint Audio Event Detection Interspeech 2018