Nicolas Obin

Biography:
<p><br />Nicolas OBIN is associate professor at the Faculty of Science and Engineering of Sorbonne University and a research scientist in the sound analysis and synthesis team from the Science and Technology of Music and Sound laboratory (<a href="https://www.ircam.fr/">Ircam</a>, CNRS, <a href="https://www.sorbonne-universite.fr/">Sorbonne University</a>). I hold a PhD thesis in computer science and telecommunications on the modeling of speech prosody and speech style for text-to-speech synthesis (2011), for which I obtained the prize for the best PhD thesis from La Fondation Des Treilles in 2011. Fascinated by sound, waves, vibrations and by the theory of information and communication, I have developed over the years a keen interest in the study and modeling behavior and communication between humans, animals and robots. My research activities cover audio signal processing, artificial intelligence, and statistical modeling of sound signals with a specialization in speech processing and human communication. My main area of research is structured generative modeling of complex human productions such as speech, singing and music with various applications in speech synthesis and transformation, multimodal virtual agent animation and humanoid robotics, and deep fakes. Lately I initiated activities in the fields of bioacoustics and sound ecology.&nbsp; I am the author of 50+ publications in international conferences or journals and I participate in numerous academic and industrial collaborative research projects. I am a member of the GdR TAL and the French <a href="https://www.levoicelab.org/">Voice Lab</a> initiative for the promotion of the French language and digital sovereignty in voice technologies.<br /><br />I am responsible at Sorbonne University for the Master's degree in <a href="https://sciences.sorbonne-universite.fr/formation-sciences/masters/master-automatique-robotique/parcours-ingenierie-des-systemes">Engineering of Intelligent Systems </a>(ISI) in which I teach digital audio signal processing, deep learning, and biometrics. I am co-responsible for <a href="https://fc.sorbonne-universite.fr/nos-offres/ia-deep-learning-par-la-pratique/">Deep Learning by Practice</a> professional training delivered by Sorbonne University, I regularly give conferences and interviews for prestigious French schools, institutions, and medias (Coll&egrave;ge de France, Ecole Normale Sup&eacute;rieure, Science Po, CNIL, Les Napol&eacute;ons, Le Monde, T&eacute;l&eacute;rama, TF1, France Culture, France 5, Arte). I am the founder of <a href="https://www.sorbonne-universite.fr/evenements/deep-voice-paris">DeepVoice, Paris</a> (since 2020) the annual Parisian event on voice technologies and artificial intelligence, SophIA (2021): the student association of Sorbonne University for Artificial Intelligence in collaboration with the&nbsp; Sorbonne Center for Artificial Intelligence (SCAI), and Fast-Forward (2022) the informal and experimental meetings of science and technology and sound design in cinema.</p> <p><br />As part of my artistic commitment to Ircam, I a actively promoting digital science and technology for arts, culture, and heritage, and collaborated with renowned musicians and artists, such as: Eric Rohmer, Philippe Parreno, Roman Polansky, Leos Carrax, George Aperghis, and Alexander Schubert.</p> <p><span class="lt-line-clamp__raw-line">My full CV is available below in pdf format</span></p> <p><a href="/media/uploads/STMS/ASS/persons/nobin/CV_nicolas_obin_EN.pdf" title="CV Nicolas Obin"><span class="lt-line-clamp__raw-line"><img alt="CV nicolas obin" src="/media/uploads/STMS/ASS/logo/logo_pdf.jpg" width="69" height="68" /> </span></a></p>

App:

Model:

Id:

Fields: