Interference Reduction in Music Recordings Combining Kernel Additive Modelling and Non-Negative Matrix Factorization
This addresses interference reduction in audio recordings for music production, but it is incremental as it builds on existing KAM and NMF techniques.
The paper tackles the problem of reducing non-stationary interferences in music recordings by combining Kernel Additive Modelling (KAM) and Non-Negative Matrix Factorization (NMF), resulting in improved separation quality over a state-of-the-art method.
In live and studio recordings unexpected sound events often lead to interferences in the signal. For non-stationary interferences, sound source separation techniques can be used to reduce the interference level in the recording. In this context, we present a novel approach combining the strengths of two algorithmic families: NMF and KAM. The recent KAM approach applies robust statistics on frames selected by a source-specific kernel to perform source separation. Based on semi-supervised NMF, we extend this approach in two ways. First, we locate the interference in the recording based on detected NMF activity. Second, we improve the kernel-based frame selection by incorporating an NMF-based estimate of the clean music signal. Further, we introduce a temporal context in the kernel, taking some musical structure into account. Our experiments show improved separation quality for our proposed method over a state-of-the-art approach for interference reduction.