This is the term project for DS-GA 1013 at NYU. The goal of the project is to separate singing voice from the background music with a given song.
MIR-1K Dataset
MIR-1K Dataset, https://sites.google.com/site/unvoicedsoundseparation/mir-1k
P.-S. Huang and S. D. Chen and P. Smaragdis and M. Hasegawa-Johnson, "Singing-voice separation from monaural recordings using robust principal component analysis" Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
Colin Raffel, Brian McFee, Eric J. Humphrey, Justin Salamon, Oriol Nieto, Dawen Liang, and Daniel P. W. Ellis, "mir_eval: A Transparent Implementation of Common MIR Metrics", Proceedings of the 15th International Conference on Music Information Retrieval, 2014.