I am a researcher with the Multispeech team at Inria, Nancy - Grand Est, France, since November 2020. My current research focuses on robust audio-visual speech processing (enhancement & separation), with an emphasis on combining the expressive power of deep neural networks with statistical and probabilistic machine learning techniques, e.g., using deep generative models.
I received my PhD from Sharif University of Technology, Tehran, Iran, in April 2018. From August 2018 to October 2020, I was a postdoctoral researcher with the Perception team (now, RobotLearn team) at Inria, Grenoble, France, working with Radu Horaud and Xavier Alameda-Pineda. Prior to that, I was a visiting PhD scholar at the Information Science and Engineering Department, Royal Institute of Technology (KTH), Stockholm, Sweden, and later, a research engineer at the Automatic Control Department.