Shift-Invariant Kernel Additive Modelling for Audio Source Separation

Abstract

A major goal in blind source separation to identify and separate sources is to model their inherent characteristics. While most state-of-the-art approaches are supervised methods trained on large datasets, interest in non-data-driven approaches such as Kernel Additive Modelling (KAM) remains high due to their interpretability and adaptability. KAM performs the separation of a given source applying robust statistics on the time-frequency bins selected by a source-specific kernel function, commonly the K-NN function. This choice assumes that the source of interest repeats in both time and frequency. In practice, this assumption does not always hold. Therefore, we introduce a shift-invariant kernel function capable of identifying similar spectral content even under frequency shifts. This way, we can considerably increase the amount of suitable sound material available to the robust statistics. While this leads to an increase in separation performance, a basic formulation, however, is computationally expensive. Therefore, we additionally present acceleration techniques that lower the overall computational complexity.

Related

August 2020 | ISMIR - International Society for Music Information Retrieval Conference

Data Cleansing with Contrastive Learning for Vocal Note Event Annotations

Gabriel Meseguer-Brocal, Rachel Bittner, Simon Durand, Brian Brost

July 2020 | IJCAI - International Joint Conference on Artificial Intelligence

Seq-U-Net: A One-Dimensional Causal U-Net for Efficient Sequence Modelling

Daniel Stoller, Mi Tian, Sebastian Ewert, and Simon Dixon