Idiap on LinkedIn Idiap youtube channel Idiap on Twitter Idiap on Facebook
Personal tools
You are here: Home Research Projects


Project Office: To Get more info on the team, project management and additional activities click here

Current projects are listed below.

Former projects can be found here

European Projects H2020

4DHEART - 4DHeart: 4D analysis of heart development and regeneration using advanced light microscopy
Cardiovascular (CV) disease is a main cause of death worldwide. During adulthood, ischemic heart disease leads to heart failure and perinatally, congenital heart defects are found in over 20% of deaths. Moreover, genetic or epigenetic factors altering development can have an impact much later in life.
DEXROV - Effective Dexterous ROV Operations in Presence of Communications Latencies
DexROV will develop cost-effective technologies and methods that will enable subsea operations with fewer off-shore personnel while increasing the range, flexibility and complexity of operations that are possible.
MALORCA - Machine Learning of Speech Recognition Models for Controller Assistance
One of the main causes hampering the introduction of higher levels of automation in the Air Traffic Management (ATM) world is the intensive use of spoken language as the natural way of communication.
MUMMER - MultiModal Mall Entertainment Robot
In MuMMER ("MultiModal Mall Entertainment Robot"), we propose to address the important and growing market of consumer entertainment robotics by advancing the technologies needed to support this area of robotics, and also by explicitly addressing issues of consumer acceptance, thus creating new European business and employment opportunities in consumer robotics.
SUMMA - Scalable Understanding of Multilingual Media
Media monitoring enables the global news media to be viewed in terms of emerging trends, people in the news, and the evolution of story-lines. The massive growth in the number of broadcast and Internet media channels means that current approaches can no longer cope with the scale of the problem.
TESLA - An Adaptive Trust-based e-assesment System for Learning
Although online education is a paramount pillar of formal, non-formal and informal learning, institutions may still be reluctant to wager for a fully online educational model. As such, there is still a reliance on face-to-face assessment, since online alternatives do not have the deserved expected social recognition and reliability. Thus, the creation of an e-assessment system that will be able to provide effective proof of student identity, authorship within the integration of selected technologies in current learning activities in a scalable and cost efficient manner would be very advantageous.

Swiss National Science Foundation Projects

COMETS-M - Computational Methods for Temporal Super-resolution Microscopy
The goal of this proposal is to develop algorithms that will, in conjunction with hardware common in modern microscopes, allow breaking the temporal resolution limit imposed by slow fluorescence cameras and the scarcity of fluorescence photons in dim samples.
HFACE - Heterogeneous Face Recognition
Face recognition has existed as a field of research for more than 30 years and has been particularly active since the early 1990s. Researchers of many different fields (from psychology, pattern recognition, neuroscience, computer graphics and computer vision) have attempted to create and understand face recognition systems.
I-DRESS - Assistive Interactive robotic system for support in DRESSing
The main objective of the project is to develop a system that will provide proactive assistance with dressing to disabled users or users such as high-risk health-care workers, whose physical contact with the garments must be limited during dressing to avoid contamination.
MAAYA - Multimedia Analysis and Access for Documentation and Decipherment of Maya Epigraphy
While academics in archaeology and epigraphy have made formidable efforts over 100 years to decipher the writings of the Ancient Maya culture, located in a variety of places in Mexico and Central America, and imprinted in multiple media types and artifacts, a significant proportion of the Maya hieroglyphic corpus remains open for scholarly interpretation.
ODESSA - Online Diarization Enhanced by recent Speaker identification and Sequential learning Approaches
PHASER - Parsimonious Hierarchical Automatic Speech Recognition
The present project aims at exploiting and integrating in a principled way recent developments in posterior- based speech recognition systems, hybrid HMM/ANN systems, exploiting Hidden Markov Model (HMM) and Artificial Neural Networks (ANN), Deep Neural Networks (a particular form of ANN with deep hierarchical and nonlinear architecture), compressive sensing, sparse modeling and hierarchical sparse coding for ASR.
PLATFORM_MMD - Platform for Reproducible Acquisition, Processing, and Sharing of Dynamic, Multi-Modal Data
SMILE - Scalable Multimodal sign language Technology for sIgn language Learning and assessmEnt
The goal of the proposed project SMILE is to pioneer an assessment system for Swiss German Sign Language (Deutschschweizerische Gebärdensprache, DSGS) using automatic sign language recognition technology.
TACT-HAND - Improving control of prosthetic hands using tactile sensors and realistic machine learning
Intuitive and robust control of poly-articulated prosthetic hands by amputees is an as-yet unsolved problem, largely due to: (1) inadequate sensorization in the hand and in the human-machine interface; and (2) inadequate machine learning methods to detect the intent of the user. These problems cannot be easily solved since prosthetic hands pose severe limitations on weight, price, size, cosmetics and power consumption. They cannot be equipped with standard robotic sensors and, at the same time, a practical, reliable intent detection method is simply not yet available.
UBIMPRESSED - UBImpressed: Ubiquitous First Impressions and Ubiquitous Awareness
First impressions matter. When we meet people for the first time, we quickly form impressions about them based on their nonverbal behavior and spoken words. Specifically in the workplace, impressions affect key outcomes like being hired or promoted, and are critical in entire sectors of the economy including sales, service, and hospitality.
UNITS - Unified Speech Processing Framework for Trustworthy Speaker Recognition
The goal of automatic speaker recognition task is to recognize persons through their voice. Automatic speaker verification is a subtest of speaker recognition task where the goal is to verify or authenticate a person. State-of-the-art speaker verification systems typically model short-term spectrum based features such as mel frequency cepstral coefficients (MFCCs) through a generative model such as, Gaussian mixture models (GMMs) and employ a series of compensation methods to achieve low error rates. This has two main limitations. First, the approach necessitates availability of sufficient training data for each speaker for robust modeling and sufficient test data to apply the series of compensation techniques to verify a speaker. Second, the speaker verification system is prone to malicious attacks such as through voice conversion (VC) system, text-to-speech (TTS) system. The main reason is that the front-end feature and back-end models of speaker verification system, namely, MFCC and GMMs, are similar to that of VC system and TTS system.
WILDTRACK - Tracking in the Wild
YOUTH@NIGHT - Youth@Night – A multi-disciplinary multi-method study of young people's outgoing and drinking behaviors

Commission for Technology and Innovation (CTI)

3DFINGERVEIN - 3D FingerVein Biometrics
The aim of this project is R&D and marketing of an integrated low-cost solution for emerging countries to reliably identify people using 3D finger-vein biometrics.
BIOWAVE - BIOWAVE pre-product, a BIOmetric Watch Activated by VEins
The project is the realisation of the BIOWAVE pre-product: a biometric watch activated by veins recognition.
DIGIT_ARENA - real-time perimeter board content digital replacement
Sport events now use dynamic advertisement by means of LED pitch perimeter boards.
ESGEM - Enhanced Swiss German mEdia Monitoring
The aim of ESGEM is to significantly enhance Swiss media monitoring by accommodating Swiss German dialect broadcasts and turning them into searchable text.
FARGO - Convenient and Secure 3D Face Recognition based on RGB-D Cameras
Since the release of the Microsoft Kinect in 2010, there has been a rapid expansion of low-cost depth sensors, also known as RGB-D cameras.
IMIM - Intelligent Monitoring for In-line Manufacturing
This project aims at developing an in line, learning based quality control for laminate welding.
SWISKO - Swiss-Korean project to develop and integrate new wearable sensors into the existing DomoSafety ambient sensor system.
SWISKO aims at building an e-health service for older people living at home combining wearable devices with the existing Domo Safety ambient sensor system.
VIEW-2 - Visibility Improvement for Events Webcasting
This project aims at developing innovative solutions to (1) improve the quality of multimedia presentation structuring and indexing by relying on several methodologies, like deep-neural networks for OCR slide processing, or active learning applied to ASR and OCR outputs to automatically generate semantic keywords; (2) using those indexes and keywords to improve the referencing of these presentation on the web.

The Ark Foundation

ELEARNING-VALAIS_3.0 - eLearning-Valais 3.0
Le projet eLearning-Valais 3.0. a l’ambition de développer et d’implémenter des solutions innovantes pour favoriser l’apprentissage dans l’enseignement et augmenter l’employabilité.
LIFE - PdG-fatigue
L’objectif de ce projet est de réunir diverses compétences, matériels et savoir-faire autour de la caractérisation physiologique de la Fatigue chez les sportifs.

Industrial Projects

NMTBENCHMARK - Name Training and Benchmarking Neural MT and ASR Systems for Swiss Languages
This document is a proposal for work on neural machine translation (MT) and automatic speech recognition (ASR) technology by the Idiap Research Institute.


CREM-IDIAP - Pour une recherche fondamentale et appliquée au service des systèmes énergétiques territoriaux en Valais
A terme, ce projet s’inscrit dans l’ambition de mettre en place un pôle de recherche universitaire CREM-Idiap dans le domaine de l’Informatique énergétique.
liveHeart - The Cellular Basis of Cardiac Development Revealead by Live Imaging
Heart pumping and shaping take place concomitantly during embryonic development. These two processes require a tight coordination between mechanical forces and tissue morphogenesis.
MACADAMS - Modifying Adhoc Centralised Advertisement with Digit Arena Multicast over Satellite
The goal of the project is to build and deliver a complete "stadium to broadcaster" integrated value chain delivering the most reliable and effective custom live advertisement replacement solution.
MASH-2 - Massive Sets of Heuristics for Machine Learning II
MCSC - Mi Casa es Su Casa
Understanding Peer Accommodation in Developed and Developing Countries
OMSI-2015_ARMASUISSE - Objective Measurement of Speech Intelligibility
RECAPP - Making speech technology accessible to Swiss people
SENSECITYVITY - Mobile Sensing, Urban Awareness, and Collective Action
The project goal is to engage citizens as factors of social change through the use of mobile technologies as tools that can improve the understanding of socio-urban problems in cities, neighborhoods, and communities.
SWAN - Secure Access Control over Wide Area Network
Crimes involving illegal access to accounts is simpler than ever based on the widespread password-based approach, which is proven to be vulnerable and no longer user-friendly.
VALAIS+ - Valais+ Une plateforme pour mieux connaître l’espace de vie du canton
Le projet Valais+ vise à construire une plateforme collaborative conçue pour la collecte d’informations de première main sur l’espace de vie valaisan, par et pour les habitants du Valais.

Document Actions