A Neural Beam Filter for Real-time Multi-channel Speech Enhancement
This work addresses speech enhancement for real-time applications, but it appears incremental as it builds on existing beamforming and neural network approaches.
The paper tackled the problem of multi-channel speech enhancement by proposing a causal neural beam filter that exploits spatial-spectral information in the beam domain, achieving superior performance over state-of-the-art methods on a dataset based on the DNS-Challenge.
Most deep learning-based multi-channel speech enhancement methods focus on designing a set of beamforming coefficients to directly filter the low signal-to-noise ratio signals received by microphones, which hinders the performance of these approaches. To handle these problems, this paper designs a causal neural beam filter that fully exploits the spatial-spectral information in the beam domain. Specifically, multiple beams are designed to steer towards all directions using a parameterized super-directive beamformer in the first stage. After that, the neural spatial filter is learned by simultaneously modeling the spatial and spectral discriminability of the speech and the interference, so as to extract the desired speech coarsely in the second stage. Finally, to further suppress the interference components especially at low frequencies, a residual estimation module is adopted to refine the output of the second stage. Experimental results demonstrate that the proposed approach outperforms many state-of-the-art multi-channel methods on the generated multi-channel speech dataset based on the DNS-Challenge dataset.