Interference Reduction in Music Recordings Combining Kernel Additive Modelling and Non-Negative Matrix Factorization

When recording music in a live or studio scenario, 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 sound source separation methods, 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 musical structure into account. Our experiments show improved separation quality for our proposed method over state-of-the-art methods for interference reduction.