On the Importance of Temporal Context in Proximity Kernels: A Vocal Separation Case Study

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.