Hi, I am Nasser!

Bio

I am a PhD fellow at the Multispeech team, affiliated with the Université de Lorraine, CNRS, and Inria (Loria). My research, under the supervision of Dr. Romain Serizel and Dr. Paul Magron, focuses on developing an objective function to enhance deep neural network (DNN) speech enhancement (SE) models, specifically targeting sensorineural hearing loss. As part of the REFINED ANR project, I collaborate closely with the Pasteur Institute (Paris), which contributes to the medical aspects of the project, and CEA (Paris) which focuses on optimizing these models for embedded systems.

Research Interests

My broader interests include:

• Speech intelligibility and speech perception loss functions
• DNN-based speech enhancement algorithms
• Low resource languages and their speech/text language processing applications