Postdoc Opportunity: Enhancing Audio-Visual Speech with Deep Generative Models at Inria, France

Join the cutting-edge research in audiovisual speech enhancement at Inria, France! We are offering a postdoctoral position within the ANR project REAVISE (Robust and Efficient Deep Learning-based Audiovisual Speech Enhancement) in the Multispeech team. Your role will be to contribute to the development of a unified framework for robust and generalizable audiovisual speech enhancement under the co-supervision of Mostafa Sadeghi, Xavier Alameda-Pineda, and Romain Serizel.

The successful candidate will work at Inria Nancy, France, starting from October 2024 (flexible) for a duration of two years. This is an exceptional opportunity to expand your knowledge and skills in deep generative models and audiovisual speech enhancement, while working in a dynamic and collaborative research environment.

To apply, please visit this link.

Feel free to share this opportunity with anyone who might be interested.