Search

DiSCogs aims at solving fundamental sound processing issues in order to place speech at the center of a new hands-free and flexible communication experience, exploiting the many devices equipped with microphones that populate our everyday life. I propose to apply machine learning methods based on de

TheVoice project aims to create voices for audiovisual production in the field of the creative, cultural, and entertainment industry. The facts are simple: today, the production of voices is exclusively carried out by humans in a sector almost exclusively digital. The scientific objectives of the

The goal of the ADDICTE project (Distributional analysis in specialized domain) is to propose an operational solution to the distributional semantic analysis in specialized domain to construct semantico-conceptual representations of the domain (domain ontologies, thesaurus, terminological resources)

In our era of steady data deluge, there is no doubt that the design of efficient techniques to extract knowledge from massive data collections or data streams has become a fundamental scientific and technological challenge bearing immense opportunities, both industrial and societal. As such, it is n

In many scientific applications, increasingly-large datasets are being acquired to describe more accurately biological or physical phenomena. While the dimensionality of the resulting measures has increased, the number of samples available is often limited, due to physical or financial limits. This

As a general modelling tool, graphs are gaining increasing attention. They capture the interactions of enti- ties in an easily comprehensible way and yet provide a rich model of the underlying structure. As information technology scrapes up ever more data in diverse areas of human activities, it bec

In recent years, computer vision has made several breakthroughs by using very large databases to train deep Convolutional Neural Networks (CNNs). In parallel, a lot of efforts have been invested to digitalize heritage artifacts, such as museum collections or archive images, that are now publicly acc

The society at large requests access to available data from various bodies: governments, universities, cultural actors, etc. This has led to the release of a vast quantity of linked data, i.e., data expressed in semantic web formalisms (RDF). Part of the added value of linked data lies in the links

The lexicon of a language like French is composed mainly of morphologically complex words: prefixed, suffixed, converted or compound. This structural information is generally available in the etymological sections of dictionaries, but the variability of its formulation makes it difficult to exploit.

The advent of parallelism in supercomputers, in embedded systems, and in more classical end-user computers increases the need for high-level code optimization and improved compilers. Being able to deal with the complexity of the upcoming software and hardware is one of the main challenges of the com

Le projet Modelisation Intérieur/Extérieur de Bâtiments (BIOM) vise à la modélisation automatique et simultanée de l'intérieur et de l'extérieur de bâtiments à partir de données d'acquisition image et Lidar (nuages de points denses). L'objectif est d'atteindre une représentation 3D complète, précise

This project is in the area of data analysis of cosmological data sets as collected by contemporary and forthcoming observatories. This is one of the most dynamic areas of modern cosmology. Our specific target are data sets of Cosmic Microwave Background (CMB) anisotropies, measurements of which hav

The quantification, understanding and prediction of the dynamics of multiphase flows is essential for gaining insight in natural phenomena and for designing engineering devices. Examples range from galaxy formations and volcanic eruptions to solar hydrogen generators and blood separating microchip

The fields of high dimensional statistics, modern inference and machine learning have witnessed transformative changes in the last few years. In particular, recent algorithmic advances on deep networks have convincingly shown that it is possible to learn non-trivial features in data in an unsupervis

Imaging what is inaccessible to direct observation, based on elastic waves, is a major issue with a wide range of applications of high societal and economic impact. In this project we aim at drastically improving the resolution of seismic tomography to produce enhanced finely-resolved images in a do

The advances in medical imaging require to develop quantitative or semi-quantitative methods to improve accuracy in the image analysis results. Advances in medical image analysis provide such tools, but there is still an important gap regarding pediatric brain imaging, even though there is an increa

The ReVeRY project will design a specific GRID OF CAMERAS, a cost-efficient system that acquires at once several viewpoints under several exposures and will convert a multiview, multiexposed, video stream into a high quality rich media. In the last two decades, industries and researchers proposed si

The project "Fast solvers for robust discretisations in CFD" will provide scalable, robust linear solvers for Compatible Discrete Operator (CDO) and Hybrid High Order (HHO) discretisations in industrial computational fluid dynamics (CFD) applications. The CDO and HHO discretisations combine the fol

Machine learning has inspired new markets and applications by extracting new insights from complex and noisy data. However, to perform such analyses, the most costly step is often to prepare the data. It entails correcting errors and inconsistencies as well as transforming the data into a single mat

Since the beginning of the industrial era, prototyping has been an important stage for manufacturers as a preliminary step before mass production. With the rise of Computer Science and recent advances of intensive computation, industry is progressively shifting from tangible prototypes to fully num

Single molecule biology is demonstrating impressive technical advances. New imaging techniques are introduced every other month, enabling the recording of large sets of biomolecules at ever-higher densities and faster temporal resolutions. Millions of localization events and hundreds of thousands of

Our Environment is perpetually subject to changes in space and time with significantly varying triggers, frequencies, magnitudes and also consequences to humans. It is critical to monitor Earth surface processes (e.g. coastal erosion, surface deformation, land cover changes) and natural ecosystem to

From quantisation to sketching for large-scale learning or infinite dimensional inverse problems, to name but a few, many different applications depend on an optimisation problem where the target is a measure. An important special case is measure approximation, which amounts to computing a proje

User-centric Internet systems, i.e., online systems that are based on user data and provide services to users, have become a major part of our lives and of our economy. With great utility they also brought security and privacy threats that became out of control in recent years and crystalized the at

The continuous proliferation and improvement of satellite sensors yields a huge volume of Earth's images with high spatial and temporal resolution. To efficiently extract the information from these data for real-life applications, it is crucial and urgent to devise new representations for these imag

A central problem in practical use of statistical models is the interpretability of a model. In many applications it is quite useful to construct a scoring system which can be defined as a sparse linear model where coefficients are simple, having few significant digits, or are even integers. Ideally