Internship: Source separation

Cambridge, Massachusetts, United States · MM · 1123


We are seeking graduate students interested in helping advance the field of source separation, speech enhancement in extreme environments, and audio reconstruction (inpainting, bandwidth extension, synthesis), using the latest developments in deep learning. The intern will collaborate with MERL researchers to derive and implement new models and optimization methods, conduct experiments, and prepare results for publication. The ideal candidate would be a senior Ph.D. student with experience in audio signal processing, speech modeling, probabilistic modeling and deep learning. The duration of the internship is expected to be 3-6 months. Positions are currently available through Summer 2018.

Research Area: Multimedia

Contact: Jonathan Le Roux

Apply for this job