Programming robot behaviour in a complex world faces challenges on multi...
Model-based reinforcement learning (MBRL) with real-time planning has sh...
Due to the dynamic nature of human language, automatic speech recognitio...
We study a class of reinforcement learning problems where the reward sig...
Human infant learning happens during exploration of the environment, by
...
Human speech can be characterized by different components, including sem...
The task of emotion recognition in conversations (ERC) benefits from the...
Large-scale commonsense knowledge bases empower a broad range of AI
appl...
Currently, the performance of Speech Emotion Recognition (SER) systems i...
Sound is one of the most informative and abundant modalities in the real...
Handling various robot action-language translation tasks flexibly is an
...
Spatial reasoning poses a particular challenge for intelligent agents an...
Understanding spatial relations is essential for intelligent agents to a...
Large datasets as required for deep learning of lip reading do not exist...
Human infants learn language while interacting with their environment in...
The aim of this work is to investigate the impact of crossmodal
self-sup...
Lifelong learning is a long-standing aim for artificial agents that act ...
The strong relation between face and voice can aid active speaker detect...
Neural networks can be powerful function approximators, which are able t...
Reasoning about potential occlusions is essential for robots to efficien...
In recent years some researchers have explored the use of reinforcement
...
Scene graph generation aims to identify objects and their relations in
i...
In domains where computational resources and labeled data are limited, s...
Using a model of the environment, reinforcement learning agents can plan...
Human infants are able to acquire natural language seemingly easily at a...
Target speech separation refers to isolating target speech from a
multi-...
Combining model-based and model-free learning systems has been shown to
...
The recognition of emotion and dialogue acts enrich conversational analy...
Combining model-based and model-free deep reinforcement learning has sho...
Selective attention plays an essential role in information acquisition a...
Recent success in deep reinforcement learning for continuous control has...
In this paper, we describe KT-Speech-Crawler: an approach for automatic
...
Previous work on emotion recognition demonstrated a synergistic effect o...
In this paper, we present a new intrinsically motivated actor-critic
alg...
Spoken language understanding is one of the key factors in a dialogue sy...
Humans excel at continually acquiring and fine-tuning knowledge over
sus...
Dialogue act recognition is an important part of natural language
unders...
Recent approaches for dialogue act recognition have shown that context f...
Speech emotion recognition (SER) is an important aspect of effective
hum...
Acoustically expressed emotions can make communication with a robot more...
Acoustic emotion recognition aims to categorize the affective state of t...
In this work, we tackle a problem of speech emotion classification. One ...
In this work a novel method to quantify spectral ergodicity for random
m...