Voice conversion aims to transform source speech into a different target...
We present ZeroEGGS, a neural network framework for speech-driven gestur...
The goal of voice conversion is to transform source speech into a target...
This paper presents Daft-Exprt, a multi-speaker acoustic model advancing...
Non-intrusive load monitoring (NILM) is a technique that uses a single s...
Learning to disentangle and represent factors of variation in data is an...
A growing number of applications, e.g. video surveillance and medical im...
Multiple instance learning (MIL) is a form of weakly supervised learning...
Several methods have recently been proposed to analyze speech and
automa...