OBIN Nicolas

Senior Lecturer
[email protected]
https://www.stms-lab.fr/person/nicolas-obin/
Institut de recherche en Musicologie IReMus (UMR 8223)

Expertise

Discover the specialized technical skills and disciplinary affiliations of our members, who represent the federated communities of the Arts & Humanities, Science & Engineering, and Medicine within the Sorbonne University Alliance.

Communities
Digital Humanities
Mathematics, Computer Science & Robotics
Skills
Artificial emotion, Cognitive Sciences, Creative AI, Generative models

Activities

Overview the professional milestones, academic responsibilities, and international collaborations that drive our center’s double ambition to excel in both research and education.

Responsibilities

PI in multiple collaborative research projects related to audio deep fake, speech synthesis, voice conversion, and muti-modal human behavior generation

Awards

Best PhD Thesis award by Fondation Des Treilles (2011)

Selected publications

  1. K. Martin, O. Adam, N. Obin, V. Dufour (2022). Rookognise: Acoustic detection and identification of individual rooks in field recordings using multi-task neural networks, submitted to Ecological Informatics.
  2. L. Benaroya, N. Obin, M. Liuni, A. Roebel, W. Raumel, S. Argentieri (2018). Binaural Localization of Multiple Sound Sources by Non-Negative Tensor Factorization. IEEE/ACM Transactions on Audio, Speech and Language Processing, vol. 26, no 6, p. 1072-1082, February 2018
  3. F. Bous, L. Benaroya, N. Obin, A. Roebel (2022) Voice Reenactment with F0 and timing constraints and adversarial learning of conversions, in European Signal Processing Conference (EUSIPCO), Belgrade, Serbia, 2022
  4. M. Fares, C. Pelachaud, N. Obin Transformer Network for Semantically-Aware and Speech-Driven Upper-Face Generation, in European Signal Processing Conference (EUSIPCO), Belgrade, Serbia, 2022
  5. C. Le Moine, N.Obin, A. Roebel (2021). Towards End-to-End F0 Voice Conversion based on Dual-GAN with Convolutional Wavelet Kernels, in European Signal Processing Conference (EUSIPCO), Dublin, Ireland, 2021.
  6. C. Robinson, N.Obin, A. Roebel (2019). Sequence-To-Sequence Modelling of F0 for Speech Emotion Conversion, International Conference on Acoustics, Speech, and Signal Processing (ICASSP), Brighton, UK, 2019