Behavioural cloning uses a dataset of demonstrations to learn a behaviou...
To facilitate research in the direction of fine-tuning foundation models...
Our aim is to build autonomous agents that can solve tasks in environmen...
We study a novel neural architecture and its training strategies of spea...
Playing games with cheaters is not fun, and in a multi-billion-dollar vi...
Paradoxically, a Variational Autoencoder (VAE) could be pushed in two
op...
As automatic speaker verification (ASV) systems are vulnerable to spoofi...
Behavioural cloning has been extensively used to train agents and is
rec...
Speech enhancement aims to improve the perceptual quality of the speech
...
VoxCeleb datasets are widely used in speaker recognition studies. Our wo...
Reinforcement learning (RL) research focuses on general solutions that c...
Autonomous driving systems need to handle complex scenarios such as lane...
Since the invention of cinema, the manipulated videos have existed. But
...
By studying the underlying policies of decision-making agents, we can le...
In recent years, transformer models have achieved great success in natur...
MineRL 2019 competition challenged participants to train sample-efficien...
Behavioural cloning, where a computer is taught to perform a task based ...
Reinforcement learning (RL) has been successful in training agents in va...
The spoofing countermeasure (CM) systems in automatic speaker verificati...
Deep neural networks (DNN) are able to successfully process and classify...
Mapping states to actions in deep reinforcement learning is mainly based...
Training agents with reinforcement learning based techniques requires
th...
The I4U consortium was established to facilitate a joint entry to NIST
s...
The popularization of science can often be disregarded by scientists as ...
We present Toribash Learning Environment (ToriLLE), an interface with vi...
Language recognition system is typically trained directly to optimize
cl...
Voice disguise, purposeful modification of one's speaker identity with t...
This article describes the systems jointly submitted by Institute for
In...