research
∙
02/17/2022
Mitigating Closed-model Adversarial Examples with Bayesian Neural Modeling for Enhanced End-to-End Speech Recognition
In this work, we aim to enhance the system robustness of end-to-end auto...
share
research
∙
06/14/2019
Perceptual Based Adversarial Audio Attacks
Recent work has shown the possibility of adversarial attacks on automati...
research
∙
12/27/2017
A Light-Weight Multimodal Framework for Improved Environmental Audio Tagging
The lack of strong labels has severely limited the state-of-the-art full...
research
∙
12/27/2017
Multiple Instance Deep Learning for Weakly Supervised Small-Footprint Audio Event Detection
State-of-the-art audio event detection (AED) systems rely on supervised ...
research
∙
12/27/2017
Multiple Instance Deep Learning for Weakly Supervised Audio Event Detection
State-of-the-art audio event detection (AED) systems rely on supervised ...
research
∙
12/27/2017