Supervision

PhD Theses Supervision

  • S. Cuervo – Deep learning for speech perception (2022–present)
    100% supervision
    AI for speech and language perception

  • S. Baroudi – Joint speech diarization and separation (2023–present)
    40% supervision
    AI for joint speech separation and diarization

  • A. Balleroy – Large-scale exploratory modeling of early language acquisition (2023–present)
    33% supervision
    AI for speech and cognition

  • J. Cauzinille – Self-supervised representation learning of primate vocalizations, from analysis to synthesis (2022–present)
    33% supervision
    AI for bioacoustics and speech

  • C. Boittiaux – Visual localisation for long-term monitoring of the deep sea (2020–2023)
    25% supervision
    Underwater computer vision

  • P. Best – Intelligent bioacoustics for real-time prediction, detection and underwater surveillance of wildlife and manage the risk of collision with maritime traffic (2019–2022)
    33% supervision
    AI for underwater multichannel bioacoustic data

  • G. Sanchez – Study and development of video characterisation algorithms. Application to the automatic indexing of audiovisual content. (2018–2022)
    33% supervision
    Audio-visual scene analysis and self-supervised learning

  • M. Ferrari – Study of bio-inspired sonar based on the modelling of a complete transmission-propagation-reception chain. Validation on sperm whales (2017–2020)
    33% supervision
    Multichannel and multimodal underwater bioacoustics

Master Theses

  • B. Aydin (2025, 33%) – Zero-Shot and Few-Shot Classification using Marine Mammals Sound. Bioacoustics.
  • F. Amor (2024, 33%) – Data Driven modelling of Sea Ice Drift. Ocean sensing and modelling.
  • M. R. Rahman (2024, 50%) – Self-Supervised Scale Consistent Depth and Ego-motion Learning from Monocular Video for underwater robots. Underwater computer vision.
  • O. Ojekanmi (2024, 50%) – High-Fidelity 3D Reconstruction of Underwater Scenes Using NeRFs. Underwater computer vision.
  • M. S. Rahman (2024, 50%) – Enhancing Underwater Object Detection and Out-of-Distribution Detection. Underwater computer vision.
  • L. A. Grajeda (2023, 50%) – AI Framework for Human-Robot Cooperative Operation through Hand Gesture Recognition. Underwater computer vision.
  • V. L. Gomes (2023, 50%) – Learning-based control for surface vehicles. Underwater robotic control.
  • A. Kaibaldiyev (2023, 50%) – Self-supervised multimodal representations for marine robotics. Computer vision and remote sensing.
  • J. Philibert (2020, 33%) – Neural ODEs and Direct Feedback Alignment. Multichannel bioacoustics.
  • N. Thellier (2020, 33%) – Joint classification and localisation for underwater data. Multichannel bioacoustics.
  • C. Lamothe (2019, 33%) – Language constraints in unsupervised symbol discovery. Unsupervised learning on speech data.

Short Master Internships (<2 months)

  • A. Badawi (2024) – Deep learning for speech modeling.
  • E. Deowan (2024) – DRL and multi-modal sensor fusion for underwater navigation.
  • R. Rincón (2023) – Unsupervised depth estimation with deep learning.
  • O. Ojekanmi (2023) – 3D underwater scene understanding with machine learning.
  • A. Grajeda (2022) – Alternative priors for homography-based cost functions.
  • V. Gomes (2022) – Experimentation with priors for homography-based cost functions.
  • A. A. Khan (2022) – Color correction methods for underwater imaging.