Many consumer speech recognition systems are not tuned for people with s...
Consumer speech recognition systems do not work as well for many people ...
Touch is the primary way that users interact with smartphones. However,
...
Voice assistants have become an essential tool for people with various
d...
Dysfluencies and variations in speech pronunciation can severely degrade...
The ability to automatically detect stuttering events in speech could he...
Codec Avatars are a recent class of learned, photorealistic face models ...
The ability to identify and temporally segment fine-grained human action...
The dominant paradigm for video-based action segmentation is composed of...
Developing automated and semi-automated solutions for reconstructing wir...
We apply recurrent neural networks to the task of recognizing surgical
a...
Joint segmentation and classification of fine-grained actions is importa...