In conventional unsupervised multi-view clustering (MVC), learning of representations from
heterogeneous multiview data and its subsequent clustering are often separately optimized …

Many studies have shown that articulatory features can significantly improve the
performance of automatic speech recognition systems. Unfortunately, such features are not …

Though speech recognition has been widely investigated in the past decades, the role of
articulation in recognition has received scant attention. Recognition accuracy increases …

This thesis focuses on representation learning for sequence data over time or space, aiming
to improve downstream sequence prediction tasks by using the learned representations …

Ce travail de thèse vise à étudier, par le biais de la modélisation et de la simulation, les
mécanismes d'apprentissage des relations entre les sons de la parole, les gestes …

Infants learn to imitate and recognize words at an early age, but phonemic awareness
develops at a later age, guided by acquisition of literacy for example. We investigate a …

• This is the best mattress I have ever had. It is a perfect combination of firmness and
support. I have never slept better....• I hate this mattress. I can't believe I bought it. It seemed …

In order to survive in this complex world, we have to constantly obtain information about
events happening around us. A modality is a particular form of signal, from which we can …