Large Scale Neural Networks for Audio Source Separation
- Master Project
- Announcement date
- 10 Mar 2011
- Michael Wohlmayr
- Robert Peharz
- Research Areas
In principle, neural networks can learn any desired task, provided that sufficient training data is available. The currently best performance in the MNIST digit classification task was achieved by a large scale neural network, where input data is artificially altered in each training epoch.
For this project, we plan to apply large scale neural networks for the audio source separation task, where we can also generate a practically unlimited amount of training data.
- Get familiar with neural networks
- Get familiar with source separation via time frequency masking
- Compare several neural network architectures for source separation
- Write a report (around 10 pages)
This project is suited for Master students in Telematics, Audio Engineering, Electrical Engineering, Computer Science and Software Development.
- Interest in machine learning techniques.
- Good Matlab skills
Robert Peharz (email@example.com or 0316/873 4482)
Michael Wohlmayr (firstname.lastname@example.org or 0316/873 4366))
 C. Bishop, “Pattern Recognition and Machine Learning,” Springer, 2006.