Full Professors

Slim Essid

ADASP Group coordinator

representation learning, multiview learning, multimodal processing, speech processing, machine listening, MIR

Roland Badeau

machine learning, data decomposition, machine listening, MIR

Geoffroy Peeters

machine learning, machine listening, MIR

Gaël Richard

machine listening, MIR, machine learning, data decomposition, representation learning,

 

Associate Professors

Mathieu Fontaine

Bayesian methods, denoising, signal models, source separation, speech processing

 

Emeritus Professors

Yves Grenier

machine listening, MIR
signal processing, music similarity

 

PhD Students

Anton Emelchenkov

signal models, deep learning
statistics, time series, anomaly detection

Morgan Buisson

MIR, deep learning, representation learning

David Perera

deep learning, machine listening, representation learning
few-shot learning, dcase

Alain Riou

MIR, representation learning, deep learning
music generation, discrete representations

Salah Zaiem

speech processing, representation learning, machine learning, deep learning

Elio Gruttadauria

speech processing,
representation learning, speaker diarization, speech separation, online inference

Manvi Agarwal

machine learning, MIR

Aurian Quélennec

representation learning, deep learning, MIR,

Louis Bahrman

deep learning, machine learning, machine listening, speech processing
reverberation

Antonin Gagneré

deep learning, representation learning, MIR
self_supervised_learning

Bernardo Torres

deep learning, machine learning, representation learning,
signal processing, neural audio synthesis, hybrid deep learning

Victor Letzelter

Bayesian methods, representation learning, machine learning
spatio-temporal audio scene analysis

Benoît Giniès

deep learning, representation learning, MIR

Sicheng Mao

speech processing
speaker diarization, generative modeling

Clémentine Berger

deep learning,
signal processing

Xuanyu Zhuang

MIR, DCASE

Côme Peladeau

deep learning, MIR
audio effects, audio quality, differentiable signal processing

 

Postdocs

Changhong Wang

deep learning, machine listening, MIR
explainable audio models

Théo Mariotte

deep learning, machine listening, speech processing
speech separation, speaker diarization

Michel Olvera

deep learning, machine listening
DCASE

Xiaoyu Bie

deep learning
generative models, audio signal processing

 

Research Engineers

José Manuel Gil

machine learning, MIR
music generation

Joris Cosentino

source separation, speech processing, deep learning,

Paraskevas Stamatiadis

speech processing,

Maxime Coutant

real-time processing, embedded, audio software

Quoc Duong Nguyen

deep learning, machine listening
audio software

Pierre Chouteau

deep learning, machine listening
signal processing

Vishal Nagarajan

deep learning, machine listening
signal processing

 

Alumni & former members

Former Full Professors

Bertrand David   2002-

Now Dean of studies with Télécom Paris

Nicolas Moreau   2002-2010

Now Retired

 

Former Associate Professors

Alexandre Gramfort   2012-2017

Now Inria Researcher

classification, EEG, machine learning, representation learning, source separation, sparse representations

Umut Simsekli   2016-2020

Now Research Faculty with INRIA / ENS

machine learning, source separation

Jacques Prado   2002-2010

Now Retired

 

Former CNRS Researchers

Cédric Févotte   2007-2012

Now CNRS Research Director with IRIT

Bayesian methods, data decomposition, machine learning, representation learning, signal models, source separation, sparse representations

Ioana Vasilescu   2002-2005

Now CNRS researcher with LISN (Laboratoire Interdisciplinaire des Sciences du Numérique)

human centered signal processing, speech processing

 

Former PhD Students

Felix Mathieu   2020-2023

Thesis: Traitement de la phase des signaux audio dans les réseaux de neurones profonds

Florian Angulo   2021-2023

Thesis:

Achille Aknin   2019-2022

Thesis:

Laure Prétet   2019-2022

Now Research Scientist with Bridge.audio

Thesis: Metric learning for video to music recommendation

Andrea Vaglio   2018-2021

Thesis: Leveraging lyrics from audio for MIR

Javier Nistal   2018-2021

Thesis: Exploring generative adversarial networks for controllable musical audio synthesis

Kimia Nadjahi   2018-2021

Now Postdoc with Sorbonne University

Thesis: Sliced-Wasserstein distance for large-scale machine learning : theory, methodology and extensions

Karim M. Ibrahim   2018-2021

Thesis: Personalized audio auto-tagging as proxy for contextual music recommendation

Giorgia Cantisani   2018-2021

Now Postdoc with Laboratoire des Systèmes Perceptifs, ENS

Thesis: Neuro-steered music source separation

Ondřej Cífka   2018-2021

Now Data Scientist with Utopia Music

Thesis: Deep learning methods for music style transfer

Kilian Schulze-Forster   2018-2021

Thesis: Informed audio source separation with deep learning in limited data settings

Nicolas Furnon   2018-2021

Thesis: DNN-based speech enhancement in ad-hoc microphone arrays

Pierre Ablin   2016-2017

Now Postdoc with Département de Mathématiques et applications, ENS

Thesis: Exploration of multivariate EEG/MEG signals using non-stationary models

Abdeldjalil Aissa El Bey   10/2004-09/2007

Now Full Professor with IMT Atlantique

Thesis: Séparation aveugle de sources audio dans le contexte automobile

Miguel Angel Alonso Arévalo   2002-2007

Now Researcher with Dept. of Electronics & Telecommunications at CICESE, Mexico

Thesis: Extraction d'information rythmique à partir d'enregistrements musicaux

Yousra Bekhti   2015-2018

Now Data Scientist with ENGIE Impact

Thesis: Contributions to sparse source localization for MEG/EEG brain imaging

Arthur Belhomme   2014-2017

Now R&D engineer with Invoxia

Thesis: The use of phase in speech dereverberation

Nancy Bertin   -

Now CNRS researcher with IRISA

Thesis: Les factorisations en matrices non-négatives. Approches contraintes et probabilistes, application à la transcription automatique de musique polyphonique.

Michael Betser   2005-2008

Now Principal research engineer with Microsoft

Thesis: Modélisation sinusoïdale et applications à l'indexation sonore

Victor Bisot   09/2014-11/2018

Now Research engineer

Thesis: Apprentissage de représentations pour l’analyse de scènes sonores

Stanislas Chambon   2015-2018

Now Research scientist with Therapixel

Thesis: Learning from electrophysiology time series during sleep: from scoring to event detection

Tom Dupré la Tour   2015-2018

Now Postdoc with UC Berkeley

Thesis: Non-linear models for neurophysiological time series

Simon Durand   2013-2017

Now Senior Research Scientist with Spotify

Thesis: Estimation automatique des premiers temps dans un signal audio musical

Jean-Louis Durrieu   2007-2010

Now DSP Software Engineer with Sonova AG

Thesis: Automatic Transcription and Separation of the Main Melody in Polyphonic Music Signals

Valentin Emiya   2004-2008

Now Assistant Professor with Aix-Marseille University, CNRS LIS, Qarma Team

Thesis: Transcription automatique de la musique de piano

Sébastien Fenet   2010-2013

Now Consultant

Thesis: Audio-Fingerprints and Associated Indexing Strategies for the Purpose of Large-Scale Audio-Identification

Thomas Fillon   2000-2004

Now R&D signal processing engineer with RTsys

Thesis: Traitement numérique du signal acoustique pour une aide aux malentendants

Mathieu Fontaine   05/2016-06/2019

Now Post-Doc with RIKEN AIP, Kyoto, Japan

Thesis: Alpha-Stable Process for the Signal Processing

Simone Fontana   2003-2005

Thesis: Deconvolution and applications to binaural technology

Rémi Foucard   2009-2013

Now Musician with Various stages/studios

Thesis: Fusion multi-niveaux par boosting pour le tagging automatique

Charles Fox   2010-2013

Now R&D Engineer with 7Sensing Software

Thesis: Débruitage multicapteur appliqué à la téléphonie mains-libres en automobile

Benoit Fuentes   2009-2012

Now Postdoctoral researcher with Télécom Paris

Thesis: L’analyse probabiliste en composantes latentes et ses adaptations aux signaux musicaux. Application à la transcription automatique de musique et à la séparation de sources.

Magdalena Fuentes   11/2016-11/2019

Now Provost's Postdoctoral Fellow with Music and Audio Research Laboratory (MARL) and Center for Urban Science and Progress (CUSP), New York University

Thesis: Multi-scale computational rhythm analysis : a framework for sections, downbeats, beats, and microtiming

Alexandre Garcia   2016-2019

Now CPGE Professor with Lycée Chaptal

Thesis: Prédiction de modèles structurés d'opinion : aspects théoriques et méthodologiques

Sébastien Gulluni   03/2008-03/2011

Now Professional Composer / Sound designer / Music technology teacher

Thesis: Un système interactif pour l’analyse des musiques électroacoustiques

Romain Hennequin   2008-2011

Now Lead Research Scientist with Deezer Research

Thesis: Décomposition de spectrogrammes musicaux informée par des modèles de synthèse spectrale. Modélisation des variations temporelles dans les éléments sonores.

Simon Henriet   2016-2020

Now Lead Research Scientist with Smart Impulse

Thesis: On solving the non intrusive load monitoring problem in large buildings : analyses, simulations and factorization based unsupervised learning

Cyril Joder   2007-2011

Now Patent examiner with European Patent Office

Thesis: Alignement temporel musique-sur-partition par modèles graphiques discriminatifs

Xabier Jaureguiberry   10/2012-07/2015

Now R&D team lead with Delfox

Thesis: Fusion for audio source separation

Simon Leglaive   2014-2017

Now Assistant Professor with CentraleSupélec

Thesis: Modèles de mélange pour la séparation multicanale de sources sonores en milieu réverbérant

Pierre Leveau   2004-2007

Now Senior Data Scientist with Zenly (Snap)

Thesis: Décompositions Parcimonieuses Structurées: Application à la représentation objet de la musique

Paul Magron   2013-2016

Now Postdoc with Institut de Recherche en Informatique de Toulouse (IRIT)

Thesis: Phase recovery based on signal modelling: application to audio source separation

Aymeric Masurelle   11/2011 - 10/2015

Now Co-Founder & Artifical Creature Artisan with SPooN

Thesis: Reconnaissance automatique d’actions et de pas de danse issus de scènes multimodales

Manuel Moussallam   09/2009-12/2012

Now Head of Research with Deezer

Thesis: Sparse and hierarchical representations for archiving audio signals

Huy Thanh Nguyen   2017-2020

Thesis: Heavy-tailed Nature of Stochastic Gradient Descent in Deep Learning: Theoretical and Empirical Analysis

Viet Son Nguyen   2005-2009

Now enseignant - chercheur with Hanoi university of science and technology

Thesis: Etudes de caractéristiques de la langue vietnamienne en vue de sa synthèse et de sa reconnaissance automatique. Aspects statiques et dynamiques

Laurent Oudre   2007-2010

Now Full Professor with ENS Paris Saclay, Centre Borelli

Thesis: Template-based chord recognition from audio signals

Sanjeel Parekh   2016-2019

Now Postdoc with Telecom Paris S2A Team

Thesis: Learning representations for robust audio-visual scene analysis

Mathieu Ramona   09/2006-09/2009

Now Senior Research Engineer with SoundHound

Thesis: Classification automatique de flux radiophoniques par machines à vecteurs de support

François Rigaud   2010-2013

Now Research engineer with Deezer Recommendation Team

Thesis: Models of music signals informed by the physics of instruments. Application to piano music analysis by Non-negative Matrix Factorization.

Mounira Rigaud-Maazaoui   2009-2012

Now R&D researcher with Faurecia Clarion Electronics

Thesis: Source separation for robot audition

Félicien Vallet   09/2007-09/2011

Now Privacy Technologist with CNIL

Thesis: Structuration automatique de talk shows télévisés

 

Former Postdocs

Christof Weiß   2021-2021

MIR
computational music analysis, chord and key recognition, tonal representations

Dogac Basaran   10/2016-01/2018

Now Research Scientist with Audible Magic

classification, deep learning, machine learning, MIR, music transcription

Atef Ben Youssef   09/2016-12/2018

Now Head of R&D with LUDO-VIC

deep learning, human centered signal processing, machine learning, multimodal processing, speech processing

Elie Laurent Benaroya   12/2016-12/2018

Now Postdoc with IRCAM

classification, source separation

Cécilia Damon   05/2012-10/2013

Now Research engineer/Project manager with IRSN Institute, D3NSI/SVDDA Team

data decomposition, EEG, machine learning, multimodal processing, signal models, source separation

Alfred Dielmann   2010-2011

Now Senior Research Scientist with Cerence

machine learning, multimodal processing, speech processing

Angélique Drémeau   2011-2013

Now Assistant professor with ENSTA Bretagne & Lab-STICC (UMR CNRS 6285)

Bayesian methods, sparse representations

Sébastien Fenet   2014-2018

Now Consultant

Mathieu Lagrange   2008-2009

Now CNRS researcher with LS2N UMR 6004

audio scene analysis, classification, deep learning, machine learning, machine listening, representation learning, signal models, signal transformation, source separation, sparse representations

Liying Wei   -

Now Lecturer with ZHEJIANG SCI-TECH UNIVERSITY

audio scene analysis, classification

Davide Andrea Mauro   01/2013-12/2013

Now Assistant Professor with Marshall University (USA)

signal transformation

Jair Montoya Martinez   2015-2017

Now Research Scientist with Flemish institute for technological research

classification, data decomposition, EEG, machine learning, signal models, source separation

Alexey Ozerov   02/2008-07/2009

Now Senior Scientist with InterDigital

audio scene analysis, Bayesian methods, classification, machine listening, source separation

François Rigaud   01/2014-07/2014

Now Research engineer with Deezer Recommendation Team

deep learning, denoising, MIR, music transcription, signal models, source separation

Mounira Rigaud-Maazaoui   2012-2014

Now R&D researcher with Faurecia Clarion Electronics

audio scene analysis, denoising, source separation, speech processing

Jean-Baptiste Schiratti   10/2016-07/2018

Now Medical Imaging Team Lead with OWKIN

classification, deep learning, EEG, machine learning

Romain Serizel   2014-2016

Now Associate Professor with Université de Lorraine/Loria

audio scene analysis, classification, machine listening, speech processing

Umut Simsekli   2015-2016

Now Research Faculty with INRIA / ENS

machine learning, source separation

 

Former Research Engineers

Thomas Fillon   12/2004-05/2005 | 11/2008-03/2013

Now R&D signal processing engineer with RTsys

classification, denoising, human centered signal processing, machine learning, MIR, speech processing

François Rigaud   2018-2020

Now Research engineer with Deezer Recommendation Team

deep learning, denoising, MIR, music transcription, signal models, source separation

 

And many more...