Singing voice separation with deep U-Net convolutional networks

Jansson, A., Humphrey, E., Montecchio, N. , Bittner, R., Kumar, A. & Weyde, T. ORCID: 0000-0001-8028-9905 (2017). Singing voice separation with deep U-Net convolutional networks. Paper presented at the 18th International Society for Music Information Retrieval Conference, 23-27 Oct 2017, Suzhou, China.

Abstract

The decomposition of a music audio signal into its vocal and backing track components is analogous to image-to-image translation, where a mixed spectrogram is transformed into its constituent sources. We propose a novel application of the U-Net architecture — initially developed for medical imaging — for the task of source separation, given its proven capacity for recreating the fine, low-level detail required for high-quality audio reproduction. Through both quantitative evaluation and subjective assessment, experiments demonstrate that the proposed algorithm achieves state-of-the-art performance.