Associate Professor in Speech and Audio Technologies Université Pierre et Marie Curie - Sorbonne Universités Laboratoire Sciences et Technologies de la Musique et du Son Ircam - Centre Pompidou Contact

I am associate professor in speech, audio, and music technologies at Ircam-Centre Pompidou, UPMC-Sorbonne Universités. I received a MSc degree in Acoustics, Signal Processing, and Computer science applied to Music and a Ph.D. in Computer Sciences from the University of Paris VI in 2006 and 2011. In 2006, I was a visiting researcher at CNMAT (Center for New Music and Audio Technologies) at the University of California, Berkeley.  I have a PhD. in computer sciences on the modeling of speech prosody and speaking style for text-to-speech synthesis (2011), and a master degree in music, art, and aesthetics (2007). I received the award for the best French Ph.D. thesis in computational sciences from ‘‘La Fondation Des Treilles'' in 2011. I am passionate and deeply involved in the promotion of audio technologies for creation, art, and culture. My main research interests cover signal processing and machine learning with application to speech synthesis, voice conversion, and machine listening.

Research Interests

• Speech synthesis, voice conversion

• Machine listening (detection/localization/separation)

• Computational musicology

Positions

[2013-] Associate Professor, Université Pierre et Marie Curie - Sorbonne Universités, Laboratoire Sciences et Technologie de la Musique et du Son, Ircam - Centre Pompidou

[2011] PhD Thesis, "MeLos: Analysis and Modelling of Speech Prosody and Speaking Style", Ircam-UPMC

[2006] Master degree, Master in Acoustics, Signal Processing and Computer Sciences applied to Music (ATIAM), Université Pierre et Marie Curie.

Research Projects

[2017-2021] TheVoice // voice design for the creatives industries, ANR : principal investigator, voice identity conversion, voice recommandation

[2015-2016] ROUTE // RObot à l'EcoUTE, Emergence Sorbonne Universités : principal investigator, binaural localization by non-negative tensor factorization

[2014-2017] ChaNTeR (Chant Numérique avec contrôle Temps Réel), ANR : participation.

[2011-2013] VOICE4GAMES, FEDER: principal investigator, automatic voice casting

[2007-2011] Rhapsodie (Corpus prosodique de référence en français parlé), ANR : participation, responsable de tâches multiples.

[2005-2008] VIVOS (Création de voix expressives : applications multimédia), RIAM : participation. 

Lectures

• Students Project / Projet Intégratif (M2 Sciences pour l'Ingénieur)

• Advanced Image and Audio Processing / Traitement Avancé des Images et du Son (M2 Sciences pour l'Ingénieur)

• Image and Audio Signal Processing / Traitement de l'Image et du Signal Audio (M1 Sciences pour l'Ingénieur)

• Information Theory / Traitement de l'Information (M1 Sciences pour l'Ingénieur)

• Python programming / Eléments de programmation (L1 Sciences et Technologies)

• Referent Teacher / Enseignant Référent (L1 Sciences et Technologies)

For a detailed profile please follow this link