Implicit Neural Spatial Filtering for Multichannel Source Separation in the Waveform Domain
This addresses source separation for audio processing applications, but it is incremental as it builds on existing methods without a major breakthrough.
The paper tackles the problem of separating moving sound sources in dynamic acoustic scenes by dividing the scene into spatial regions for target and interfering sources, and it matches the performance of an oracle beamformer with a state-of-the-art single-channel enhancement network.
We present a single-stage casual waveform-to-waveform multichannel model that can separate moving sound sources based on their broad spatial locations in a dynamic acoustic scene. We divide the scene into two spatial regions containing, respectively, the target and the interfering sound sources. The model is trained end-to-end and performs spatial processing implicitly, without any components based on traditional processing or use of hand-crafted spatial features. We evaluate the proposed model on a real-world dataset and show that the model matches the performance of an oracle beamformer followed by a state-of-the-art single-channel enhancement network.