We developed dysarthric speech intelligibility classifiers on 551,176
di...
Automatic Speech Recognition (ASR) in medical contexts has the potential...
Word Error Rate (WER) is the primary metric used to assess automatic spe...
We present Generalizable NeRF Transformer (GNT), a pure, unified
transfo...
Motivated by the need for accelerating text entry in augmentative and
al...
Recent advances in self-supervision have dramatically improved the quali...
We analyze a dataset of retinal images using linear probes: linear regre...
Automatic classification of disordered speech can provide an objective t...
Integrated Gradients (IG) is a commonly used feature attribution method ...
Diabetic retinopathy (DR) screening is instrumental in preventing blindn...
Model explanation techniques play a critical role in understanding the s...
Symbolic techniques based on Satisfiability Modulo Theory (SMT) solvers ...
Confounding variables are a well known source of nuisance in biomedical
...
Diabetic eye disease is one of the fastest growing causes of preventable...
Each year, the treatment decisions for more than 230,000 breast cancer
p...
Image segmentation from referring expressions is a joint vision and lang...
Recent captioning models are limited in their ability to scale and descr...
This paper investigates how linguistic knowledge mined from large text
c...
While recent deep neural network models have achieved promising results ...
Real-world videos often have complex dynamics; and methods for generatin...
Solving the visual symbol grounding problem has long been a goal of
arti...
Models based on deep convolutional networks have dominated recent image
...