Projects
Digital signal processing for digital communication, audio- and speech signal processing KU Leuven
Marc Moonen supervises a research team of pre- and postdoctoral researchers performing research in digital signal processing algorithms design and evaluation, for digital communication and audio- and speech signal processing. Digital communication activities are targeted towards physical layer processing (e.g. equalization, multiple-access, interference/crosstalk cancellation and MIMO transmission techniques) and resource allocation, in ...
A holistic approach to the design of integrated and distributed digital signal processing algorithms for audio and speech communication devices KU Leuven
Cooperative Signal Processing Solutions for IoT-based Multi-User Speech Communication Systems KU Leuven
Models of Pathological Speech for Diagnosis and Speech Recognition KU Leuven
Lateralization patterns in (a)typical speech dominants Ghent University
The human brain processes cognitive functions asymmetrically but it remains surprisingly unclear how functions co-lateralize, how large the variability in the degree of laterality is, and what consequences atypical lateralization has for interhemispheric communication and task performance. The current project aims to chart the laterality of language (sub)processes (speech production, reading, auditory processing) and non-linguistic functions ...
Sabbatical Jan Wouters: Speech and Hearing: basic study for the preparation of a grant application and a scientific book KU Leuven
In the last years of my academic career I want to start with an intense study period in which I want to prepare and outline future lines of my research (and that are important for the future of hearing research at KU Leuven). Intensive study work and a number of study visits to foreign colleagues should provide the necessary input to develop an innovative and up-to-date research program for the coming years. This sabbatical can culminate in a ...
Deep neural networks as a model of speech perception KU Leuven
VASI: Vocabulary Acquisition from Speech and Images. KU Leuven
Efficient Language Modeling for Automatic Speech Recognition KU Leuven
Since the advent of deep learning, automatic speech recognition (ASR), like many other fields, has advanced significantly. Both the acoustic model and the language model are now based on artificial neural networks which has yielded drastic improvements in recognition accuracy. However, whereas the state-of-the-art acoustic models have been integrated directly into the core of most if not all speech recognizers, the same cannot be said of ...