Audio Separation Using Deep Neural Networks

We are sorry, this position has been filled.

Using a novel deep learning framework for single microphone speech separation, the goal of the project is to design a system that effectively segregates multiple audio sources.

Lab: Neural Acoustic Processing Lab, MUDD 1339

Direct Supervisor: Nima Mesgarani

Position Dates: 5/15/2017 - 8/31/2017

Hours per Week: 20

Paid Position: No

Credit: Yes

Qualifications: N/A

Eligibility: Senior, Master's; SEAS only

Professor Nima Mesgarani, nm2764@columbia.edu, CEPSR 910