Search papers, labs, and topics across Lattice.
This paper introduces a neural dereverberation and directional filtering (NDDF) approach that enhances the reconstruction of virtual directional microphone (VDM) signals in reverberant environments. By employing both discriminative and GAN-based models, the NDDF consistently outperforms traditional cascaded methods, particularly excelling in high-order VDM scenarios. Additionally, the authors present a novel directivity pattern estimation method that utilizes only input and output signals, streamlining the spatial filtering process.
GAN-based NDDF not only outperforms traditional methods in reverberant conditions but also simplifies directivity pattern estimation, revolutionizing spatial sound capture.
Recently, neural directional filtering (NDF) enables reconstruction of a virtual directional microphone (VDM) with a desired directivity pattern, accurately rendering multi-source scenes by preserving spatial cues. In strongly reverberant environments, spatial cues become perceptually difficult to distinguish, limiting NDF-based spatial sound capture. This paper addresses this limitation with three contributions: First, we propose a neural dereverberation and directional filtering (NDDF) approach to reconstruct dereverberated VDM signals. Second, NDDF is implemented with discriminatively trained and generative adversarial network (GAN)-based models, compared with cascaded dereverberation and directional-filtering baselines. Experimental results indicate that the NDDF consistently surpasses the cascaded baselines. Additionally, the GAN-based NDDF outperforms the discriminative variant when addressing a high-order VDM target. Third, we introduce a method for directivity pattern estimation that relies solely on the input and output signals. This method is suitable for signal-mapping-based spatial filtering, which synthesizes the output signal directly without explicit filtering or masking.
