Joseph Keshet

Constant Random Perturbations Provide Adversarial Robustness with Minimal Effect on Accuracy

2021 · arXiv (Cornell University)

This paper proposes an attack-independent (non-adversarial training) technique for improving adversarial robustness of neural network models, with minimal loss of standard accuracy. We suggest creating a neighborhood around each training example, such that the label …

THOR: Threshold-Based Ranking Loss for Ordinal Regression

2022 · arXiv (Cornell University)

In this work, we present a regression-based ordinal regression algorithm for supervised classification of instances into ordinal categories. In contrast to previous methods, in this work the decision boundaries between categories are predefined, and the …

Correcting Mispronunciations in Speech using Spectrogram Inpainting

2022 · Interspeech 2022

Learning a new language involves constantly comparing speech productions with reference productions from the environment.Early in speech acquisition, children make articulatory adjustments to match their caregivers' speech.Grownup learners of a language tweak their speech to …