Musical source separation methods exploit source-specific spectral characteristics to facilitate the decomposition process. Kernel Additive Modelling (KAM) models a source applying robust statistics to time-frequency bins as specified by a source-specific kernel, a function defining similarity between bins. Kernels in existing approaches are typically defined using metrics between single time frames. In the presence of noise and other sound sources information from a single-frame, however, turns out to be unreliable and often incorrect frames are selected as similar. In this paper, we incorporate a temporal context into the kernel to provide additional information stabilizing the similarity search. Evaluated in the context of vocal separation, our simple extension led to a considerable improvement in separation quality compared to previous kernels.
Yela, Delia Fano; Ewert, Sebastian; Fitzgerald, Derry; Sandler, Mark
Affiliations: Queen Mary University of London, London, UK; Cork Institute of Technology, Cork, Ireland(See document for exact affiliation information.)
AES Conference: 2017 AES International Conference on Semantic Audio (June 2017)
Paper Number: 1-2
Publication Date: June 13, 2017
Subject: Audio Source Separation
No AES members have commented on this paper yet.
If you are not yet an AES member and have something important to say about this paper then we urge you to join the AES today and make your voice heard. You can join online today by clicking here.