In online conferencing applications, estimating the perceived quality of...
Fine-tuning an Automatic Speech Recognition (ASR) model to new domains
r...
In dysarthric speech recognition, data scarcity and the vast diversity
b...
Alzheimer's disease (AD) is a progressive neurodegenerative disease most...
Objective. When a person listens to continuous speech, a corresponding
r...
Most spoken language understanding systems use a pipeline approach compo...
We explore the benefits that multitask learning offer to speech processi...
We study the impact of visual assistance for automated audio captioning....
Adapting a trained Automatic Speech Recognition (ASR) model to new tasks...
The scarcity of training data and the large speaker variation in dysarth...
In this technical report, the systems we submitted for subtask 1B of the...
In this technical report, the systems we submitted for subtask 4 of the ...
TV subtitles are a rich source of transcriptions of many types of speech...
Speech quality in online conferencing applications is typically assessed...
Many state-of-the-art systems for audio tagging and sound event detectio...
Large-scale sound recognition data sets typically consist of acoustic
re...
The electroencephalogram (EEG) is a powerful method to understand how th...
End-to-end spoken language understanding (SLU) systems benefit from
pret...
Adapting Automatic Speech Recognition (ASR) models to new domains leads ...
The choice of an optimal time-frequency resolution is usually a difficul...
Recent research in speech processing exhibits a growing interest in
unsu...
Decoding the speech signal that a person is listening to from the human ...
We inspect the long-term learning ability of Long Short-Term Memory lang...
We study the merit of transfer learning for two sound recognition proble...
Objective: Currently, only behavioral speech understanding tests are
ava...
Designing a speech-to-intent (S2I) agent which maps the users' spoken
co...
Long short-term memory recurrent neural networks (LSTM-RNNs) are conside...
This paper examines the applicability in realistic scenarios of two deep...
In recent years there have been many deep learning approaches towards th...
We tackle the task of environmental event classification by drawing
insp...
We present a framework for the induction of semantic frames from utteran...
Neural cache language models (LMs) extend the idea of regular cache lang...
With deep learning approaches becoming state-of-the-art in many speech (...
Research in deep learning for multi-speaker source separation has receiv...
We present a framework for analyzing what the state in RNNs remembers fr...
Designing a spoken language understanding system for command-and-control...
In Flanders, all TV shows are subtitled. However, the process of subtitl...
Lately there have been novel developments in deep learning towards solvi...
We present a Character-Word Long Short-Term Memory Language Model which ...