All theses
2025
| Efficient Adaptation for Speech Technology, , EPFL, 2025 |
|
| Face morphing attacks in the era of deepfakes: risks, detection & source attribution, , Université de Lausanne, 2025 |
|
| Nonparametric Variational Information Bottleneck: Attention-based Architectures as Latent Variable Models, , EPFL, 2025 |
[URL] |
| Robot Manipulation with Geometric Algebra: A Unified Geometric Framework for Control and Optimization, , EDEE, 2025 |
|
| Transferability of Learnt Speech Representations for Decoding Non-Human Vocal Communication, , Ecole Polytechnique Fédérale de Lausanne, 2025 |
|
2024
| A Stochastic Approach to Contact-rich Manipulation, , Ecole Polytechnique Fédérale de Lausanne, 2024 |
|
| Biologically Inspired Spiking Neural Networks for Speech Recognition, , EPFL/EDEE, 2024 |
[DOI] |
| Discovering Meaningful Units from Text Sequences, , EPFL, 2024 |
[DOI] [URL] |
| Extending Capabilities of Attention-based Models, , EDIC - EPFL, 2024 |
|
| On the Information in Deep Biometric Templates: from Vulnerability of Unprotected Templates to Leakage in Protected Templates, , EPFL, 2024 |
[DOI] [URL] |
| Performing And Detecting Backdoor Attacks on Face Recognition Algorithms, , Ecole Polytechnique Fédérale de Lausanne, 2024 |
|
| Robot Learning using Tensor Networks, , Ecole Polytechnique Fédérale de Lausanne, 2024 |
[DOI] |
| Safe Deep Neural Networks, , EPFL, 2024 |
|
2023
| Confidence Matters : Applications to Semantic Segmentation, , École polytechnique fédérale de Lausanne, 2023 |
[DOI] |
| Data-driven urban building energy modeling in Satom (CH): The energy savings potential and use of available renewable energy sources., , and , Politecnico di Torino, 2023 |
[URL] |
| Generalization and Personalization of Machine Learning for Multimodal Mobile Sensing in Everyday Life, , EPFL, 2023 |
|
| Interpretable Representation Learning and Evaluation for Abstractive Summarization, , École polytechnique fédérale de Lausanne, 2023 |
[DOI] [URL] |
| Learning and Optimization of Anticipatory Feedback Controllers for Robot Manipulation, , École Polytechnique Fédérale de Lausanne, 2023 |
[DOI] |
| Modeling Structured Data in Attention-based Models, , EPFL, 2023 |
[URL] |
| Novel Methods For Detection And Analysis Of Atypical Aspects In Speech, , École Polytechnique Fédérale de Lausanne, 2023 |
[DOI] |
| On matching data and model in LF-MMI-based dysarthric speech recognition, , École polytechnique fédérale de Lausanne, 2023 |
[DOI] [URL] |
| Practical computational imaging by use of spatiotemporal light modulation: from simulations to applications in biological microscopy, , EPFL, 2023 |
[DOI] |
| Privacy-Preserving Machine Learning on Graphs, , EPFL, 2023 |
[DOI] |
| Sparse Autoencoders for Speech Modeling and Recognition, , École polytechnique fédérale de Lausanne, 2023 |
[DOI] |
| Text Representation Learning for Low Cost Natural Language Understanding, , École polytechnique fédérale de Lausanne, 2023 |
[DOI] [URL] |
2022
| Automatic pathological speech assessment, , École polytechnique fédérale de Lausanne, 2022 |
[DOI] |
| Controllability and Interpretability in Affective Speech Synthesis, , École polytechnique fédérale de Lausanne, 2022 |
[DOI] [URL] |
| Efficient Transformer-Based Speech Recognition, , École polytechnique fédérale de Lausanne, 2022 |
[DOI] |
| Memory of Motion for Initializing Optimization in Robotics, , École Polytechnique Fédérale de Lausanne, 2022 |
|
| Stop Wasting my FLOPS: Improving the Efficiency of Deep Learning Models, , École Polytechnique Fédérale de Lausanne, 2022 |
[DOI] |
| Using synthetic fingerprint images to test the performance of an AFIS system, , Université de Lausanne, 2022 |
|
2021
| Deep Learning Approaches for Auditory Perception in Robotics, , École polytechnique fédérale de Lausanne, 2021 |
|
| Efficient Depth-based Deep Learning Methods for Multi-Party Pose Estimation, , École polytechnique fédérale de Lausanne, 2021 |
[DOI] |
| Explainable Phonology-based Approach for Sign Language Recognition and Assessment, , Ecole Polytechnique Fédérale de Lausanne, 2021 |
|
| Gradient-based Methods for Deep Model Interpretability, , École polytechnique fédérale de Lausanne, 2021 |
[DOI] |
| Learning strategies and representations for intuitive robot learning from demonstration, , EPFL, 2021 |
|
| Modeling and Inferring Attention between Humans or for Human-Robot Interactions, , Ecole Polytechnique Federale de Lausanne, 2021 |
[DOI] [URL] |
| Novel Methods for Incorporating Prior Knowledge for Automatic Speech Assessment, , École polytechnique fédérale de Lausanne (EPFL), 2021 |
|
2020
| Accurate Nod and 3D Gaze Estimation for Social Interaction Analysis, , EDEE, EPFL, 2020 |
|
| Active Illumination and Computational Methods for Temporal and Spectral Super-Resolution Microscopy, , EPFL, 2020 |
[DOI] |
| Context is Everything: Using a Smartphone App to Capture Young People's Drinking Behaviours, Cognitions, Environments, and Consequences, , La Trobe University, Melbourne, Australia, 2020 |
[DOI] |
| Deep Generative Models and Applications, and , EPFL, 2020 |
[DOI] [URL] |
| Detection of disguised speech in forensic science by humans and automatic systems, , Université de Lausanne Ecole des Sciences Criminelles, 2020 |
|
| Discourse Phenomena in Machine Translation, , École polytechnique fédérale de Lausanne, 2020 |
|
| Product of experts for robot learning from demonstration, , EPFL, 2020 |
| Robot skills learning with Riemannian manifolds : Leveraging geometry-awareness in robot learning, optimization and control, , Ecole Polytechnique Fédérale de Lausanne, 2020 |
|
| Trustworthy Face Recognition: Improving Generalization of Deep Face Presentation Attack Detection, , École polytechnique fédérale de Lausanne, 2020 |
|
2019
| Automated Daylighting Control System based on Sky Luminance Monitoring and Lighting Computing, , and , EPFL, 2019 |
[DOI] |
| Language Independent Query by Example Spoken Term Detection, , École Polytechnique Fédérale de Lausanne, 2019 |
|
| Learning How To Recognize Faces in Heterogeneous Environments, , Ecole Polytechnique Federale de Lausanne, 2019 |
[DOI] [URL] |
| Multimodal Person Recognition in Audio-Visual Streams, , EPFL, 2019 |
[DOI] |
| Sparse and Low-rank Modeling for Automatic Speech Recognition, , EPFL, 2019 |
[DOI] |
| Trustworthy speaker recognition with minimal prior knowledge using neural networks, , Ecole polytechnique fédérale de Lausanne (EPFL), 2019 |
[DOI] [URL] |
2018
| Generative Models for Learning Robot Manipulation Skills from Humans, , Ecole Polytechnique Federale de Lausanne, 2018 |
[DOI] |
| Learning embeddings: efficient algorithms and applications, , École Polytechnique Fédérale de Lausanne, 2018 |
[DOI] |
| Novel Algorithms for Clustering, , École polytechnique fédérale de Lausanne, 2018 |
[DOI] |
| Phonetic aware techniques for Speaker Verification, , EPFL, 2018 |
|
| Theory and Algorithms for Hypothesis Transfer Learning, , EPFL, 2018 |
[DOI] |
| Word Sense Consistency in Statistical and Neural Machine Translation, , École Polytechnique Fédérale de Lausanne, 2018 |
|
2017
| Intonation Modelling for Speech Synthesis and Emphasis Preservation, , École Polytechnique Fédérale de Lausanne, 2017 |
[DOI] |
| Large-Scale Image Segmentation with Convolutional Networks, , Sciences et Techniques de l’Ingénieur (STI), 2017 |
|
| Object Detection with Active Sample Harvesting, , École Polytechnique Fédérale de Lausanne, 2017 |
|
| On Modeling the Synergy Between Acoustic and Lexical Information for Pronunciation Lexicon Development, , École polytechnique fédérale de Lausanne (EPFL), 2017 |
[DOI] |
| Visual Analysis of Maya Glyphs via Crowdsourcing and Deep Learning, , École Polytechnique Fédérale de Lausanne, 2017 |
[DOI] |
2016
| "Can you hear me now?" --- Automatic assessment of background noise intrusiveness and speech intelligibility in telecommunications, , Sciences et Techniques de l’Ingénieur (STI), 2016 |
[DOI] |
| Building Word Embeddings for Solving Natural Language Processing, , École Polytechnique Fédérale de Lausanne, 2016 |
[DOI] |
| Computational Analysis of Urban Places Using Mobile Crowdsensing, , Ecole Polytechnique Federale de Lausanne, 2016 |
[DOI] |
| Learning Explainable User Sentiment and Preferences for Information Filtering, , École Polytechnique Fédérale de Lausanne, 2016 |
[DOI] |
| Towards End-to-End Speech Recognition, , Ecole polytechnique Fédérale de Lausanne, 2016 |
[DOI] |
| Word Sequence Modeling using Deep Learning: and End-to-end Approach and its Applications, , EPFL, 2016 |
[DOI] |
2015
| 3D Gaze Estimation from Remote RGB-D Sensors, , École Polytechnique Fédérale de Lausanne, 2015 |
[DOI] |
| Automatic social role recognition and its application in structuring multiparty interactions, , EPFL, 2015 |
|
| Computational Analysis Of Behavior In Employment Interviews And Video Resumes, , École Polytechnique Fédérale de Lausanne, 2015 |
|
| Enabling speech applications using Ad-Hoc Microphone Arrays, , École Polytechnique Fédérale de Lausanne, 2015 |
|
| Statistical Models in Automatic Speech Recognition, , University of Fribourg, Department of Mathematics, 2015 |
|
| Trustworthy Biometric Verification under Spoofing Attacks: Application to the Face Mode, , École Polytechnique Fédérale de Lausanne, 2015 |
[URL] |
2014
| Discourse-level Features for Statistical Machine Translation, , École Polytechnique Fédérale de Lausanne (EPFL), 2014 |
|
| Grapheme-based Automatic Speech Recognition using Probabilistic Lexical Modeling, , École polytechnique fédérale de Lausanne, 2014 |
[DOI] |
| Human Tracking and Pose Estimation in Open Spaces, , École Polytechnique Fédérale de Lausanne (EPFL), 2014 |
|
| Inferring Visual Attention and Addressee in Human Robot Interaction, , École Polytechnique Fédérale de Lausanne (EPFL), 2014 |
|
| Saliency-based Representations and Multi-component Classifiers for Visual Scene Recognition, , École Polytechnique Fédérale de Lausanne (EPFL), 2014 |
|
| Scalable Probabilistic Models for Face and Speaker Recognition, , École Polytechnique Fédérale de Lausanne (EPFL), 2014 |
[URL] |
| Tractable Approaches to Learning and Planning in High Dimensions, , EPFL, 2014 |
[DOI] |
2013
| Automatic Personality Perception: Inferring Personality Traits from Nonverbal Vocal Behavior, , Electrical Engineering Department, EPFL, 2013 |
|
| Computational Methods for Audio-Visual Analysis of Emergent Leadership in Teams, , École Polytechnique Fédéral de Lausanne, 2013 |
|
| Learning to Learn by Exploiting Prior Knowledge, , EDIC, 2013 |
|
| Mining Conversational Social Video, , EPFL, 2013 |
|
| Model-based Sparse Component Analysis for Multiparty Distant Speech Recognition, , École Polytechnique Fédérale de Lausanne, 2013 |
|
| Multilingual speech recognition A posterior based approach, , École Polytechnique Fédérale de Lausanne (EPFL), 2013 |
|
| Object Classification and Detection in High Dimensional Feature Space, , Programme doctoral en Informatique, Communications et Information, 2013 |
|
| Similarity Learning Over Large Collaborative Networks, , and , EPFL, 2013 |
|
2012
| Alternative search techniques for face detection using location estimation and binary features, , ECOLE POLYTECHNIQUE FEDERALE DE LAUSANNE, 2012 |
|
| Data-Driven Enhancement of State Mapping-Based Cross-Lingual Speaker Adaptation, , École Polytechnique Fédérale de Lausanne, 2012 |
|
| Sequential Topic Models for Mining Recurrent Activities and their Relationships : Application to long term video recordings, , École Polytechnique Fédérale de Lausanne, 2012 |
|
| Statistical Shape Descriptors for Ancient Maya Hieroglyphs Analysis, , École Polytechnique Fédérale de Lausanne, 2012 |
|
| Unified Framework Of Feature Based Adaptation For Statistical Speech Synthesis And Recognition, , Ecole Polytechnique Federale de Lausanne (EPFL), 2012 |
|
2011
| A Probabilistic Approach to Socio-Geographic Reality Mining, , Ecole Polytechnique Fédérale de Lausanne, 2011 |
|
| Bayesian Approaches to Uncertainty in Speech Processing, , School of Computing Sciences, University of East Anglia, 2011 |
|
| Boosting Localized Features for Speaker and Speech Recognition, , Ecole Polytechnique Federale de Lausanne (EPFL), 2011 |
|
| Computational modeling of face-to-face social interaction using nonverbal behavioral cues, , Ecole Polytechnique Fédérale de Lausanne, 2011 |
|
| Modeling and understanding communities in online social media using probabilistic methods, , Ecole polytechnique fédérale de Lausanne, 2011 |
[DOI] [URL] |
| Open-ended Learning of Visual and Multi-modal Patterns, , Ecole polytechnique fédérale de Lausanne, 2011 |
|
| Privacy-Sensitive Audio Features for Conversational Speech Processing, , Ecole Polytechnique Fédérale de Lausanne, 2011 |
|
2010
| An Information Theoretic Approach to Speaker Diarization of Meeting Recordings, , Ecole polytechnique fédérale de Lausanne, 2010 |
|
| Multilayer Perceptron Based Hierarchical Acoustic Modeling for Automatic Speech Recognition, , Ecole polytechnique fédérale de Lausanne, 2010 |
|
| Social Network Analysis for Automatic Role Recognition, , Ecole Polytechnique Fédérale de Lausanne, 2010 |
|
2009
| On the design of audio features robust to the album-effect for music information retrieval., , Ecole Polytechnique Fédérale de Lausanne, 2009 |
2008
| Acoustic Models for Posterior Features in Speech Recognition, , Ecole Polytechnique Fédérale de Lausanne, 2008 |
|
| Enhancing posterior based speech recognition systems, , Ecole Polytechnique Fédérale de Lausanne, 2008 |
|
| Inference in switching linear dynamical systems applied to noise robust speech recognition of isolated digits, , Ecole Polytechnique Fédérale de Lausanne, 2008 |
|
| Machine Learning for Information Retrieval, , Ecole Polytechnique Fédérale de Lausanne, 2008 |
|
| Methods for Asynchronous and Non-Invasive EEG-Based Brain-Computer Interfaces. Towards Intelligent Brain-Actuated Wheelchairs, , University of Barcelona, 2008 |
|
| Probabilistic models for music, , Ecole Polytechnique Fédérale de Lausanne, 2008 |
[URL] |
2007
| Bayesian methods for visual multi-object tracking with applications to human activity recognition, , École Polytechnique Fédérale de Lausanne, 2007 |
|
| Error-related EEG potentials in brain-computer interfaces, , École Polytechnique Fédérale de Lausanne, 2007 |
|
| Joint Head Tracking and Pose Estimation for Visual Focus of Attention Recognition, , École Polytechnique Fédérale de Lausanne, 2007 |
|
| Learning the structure of image collections with latent aspect models, , École Polytechnique Fédérale de Lausanne, 2007 |
|
| Scene image classification and segmentation with quantized local descriptors and latent aspect modeling, , École Polytechnique Fédérale de Lausanne, 2007 |
|
2006
| Analysis and Classification of EEG Signals using Probabilistic Models for Brain Computer Interfaces, , École Polytechnique Fédérale de Lausanne, 2006 |
[DOI] [URL] |
| Ensembles for Sequence Learning, , École Polytechnique Fédérale de Lausanne, 2006 |
|
| Face Detection and Verification using Local Binary Patterns, , École Polytechnique Fédérale de Lausanne, 2006 |
|
| Machine Learning Approaches to Text Representation using Unlabeled Data, , Ecole Polytechnique Fédérale de Lausanne, 2006 |
|
| Multi-stream Processing for Noise Robust Speech Recognition, , École Polytechnique Fédérale de Lausanne, 2006 |
|
| Multi-system Biometric Authentication: Optimal Fusion and User-Specific Information, , École Polytechnique Fédérale de Lausanne, 2006 |
|
| Prior Knowledge in Kernel Methods, , École Polytechnique Fédérale de Lausanne, 2006 |
|
| Probabilistic Graphical Models for Human Interaction Analysis, , École Polytechnique Fédérale de Lausanne, 2006 |
|
| Spatio-Temporal Analysis of Spontaneous Speech with Microphone Arrays, , Ecole Polytechnique Fédérale de Lausanne, 2006 |
|
| Two-Handed Gestures for Human-Computer Interaction, , École Polytechnique Fédérale de Lausanne, 2006 |
|
2005
| Face Authentication Based on Local Features and Generative Models, , École Polytechnique Fédérale de Lausanne, 2005 |
|
| Joint Speech and Speaker Recognition, , École Polytechnique Fédérale de Lausanne, Computer Science Department, 2005 |
|
| Multimedia event modelling and recognition, , École Polytechnique Fédérale de Lausanne, 2005 |
| Using Auxiliary Sources of Knowledge for Automatic Speech Recognition, , École Polytechnique Fédérale de Lausanne, Computer Science Department, 2005 |
|
2004
| Large Scale Machine Learning, , Université de Paris VI, 2004 |
|
| Nonlinear Feature Transformations for Noise Robust Speech Recognition, , Ecole Polytechnique Fédérale de Lausanne, 2004 |
|
| Robust Audio Segmentation, , and , École Polytechnique Fédérale de Lausanne, 2004 |
|
2003
| HMM Mixtures (HMM2) for Robust Speech Recognition, , Ecole Polytechnique Federale de Lausanne, 2003 |
|
| Speech Recognition with Auxiliary Information, , École Polytechnique Fédérale de Lausanne, Computer Science Department, 2003 |
|
| Text detection and recognition in images and video sequences, , École Polytechnique Fédérale de Lausanne, 2003 |
|
2001
| PhD Thesis: Speech Analysis with Production Constraints, , École Polytechnique Fédérale de Lausanne, 2001 |
|
| Robust speech recognition based on multi-stream processing, , École Polytechnique Fédérale de Lausanne, 2001 |
|
2000
| Mixture Models for Unsupervised and Supervised Learning, , École Polytechnique Fédérale de Lausanne, Computer Science Department, 2000 |
|
| The use of Boolean concepts in general classification contexts, , Ecole Polytechnique Federale de Lausanne, 2000 |
|
1999
| Reconnaissance et Transformation de Locuteurs, , École Polytechnique Fédérale de Lausanne, 1999 |
|
1997
| Optimization of high order perceptrons, , École Polytechnique Fédérale de Lausanne, 1997 |
|
| Visual Speech and Speaker Recognition, , University of Sheffield, 1997 |
|