DOA Estimation by DNN-based Denoising and Dereverberation from Sound Intensity Vector
This work addresses improved DOA estimation for audio signal processing applications, but it is incremental as it builds on existing IV and DNN techniques.
The paper tackled the problem of direction of arrival (DOA) estimation accuracy degradation due to noise and reverberation by proposing a method that combines sound-intensity vector-based estimation with DNN-based denoising and dereverberation, achieving an average DOA error of 0.528 degrees and outperforming conventional methods.
We propose a direction of arrival (DOA) estimation method that combines sound-intensity vector (IV)-based DOA estimation and DNN-based denoising and dereverberation. Since the accuracy of IV-based DOA estimation degrades due to environmental noise and reverberation, two DNNs are used to remove such effects from the observed IVs. DOA is then estimated from the refined IVs based on the physics of wave propagation. Experiments on an open dataset showed that the average DOA error of the proposed method was 0.528 degrees, and it outperformed a conventional IV-based and DNN-based DOA estimation method.