Kavli Affiliate: Zeeshan Ahmed | First 5 Authors: Chao-Han Huck Yang, Zeeshan Ahmed, Yile Gu, Joseph Szurley, Roger Ren | Summary: In this work, we aim to enhance the system robustness of end-to-end automatic speech recognition (ASR) against adversarially-noisy speech examples. We focus on a rigorous and empirical "closed-model adversarial robustness" setting (e.g., on-device or […]
Continue.. Mitigating Closed-model Adversarial Examples with Bayesian Neural Modeling for Enhanced End-to-End Speech Recognition