The study of speech disorders can benefit greatly from time-aligned data...
Automated audio captioning is multi-modal translation task that aim to
g...
There is an imminent need for guidelines and standard test sets to allow...
Modern speech recognition systems exhibits rapid performance degradation...
The recent state of the art on monocular 3D face reconstruction from ima...
Recent deep learning Text-to-Speech (TTS) systems have achieved impressi...
Aphasia is a common speech and language disorder, typically caused by a ...
In this paper, we introduce EmpBot: an end-to-end empathetic chatbot.
Em...
This brief literature review studies the problem of audiovisual speech
s...