Direct source and early reflections localization using deep deconvolution network under reverberant environment
This work addresses sound source localization in challenging acoustic conditions, which is important for applications like audio processing and robotics, but it appears incremental as it builds on existing deconvolution and network methods.
The paper tackled the problem of localizing direct sound sources and early reflections in reverberant environments by proposing a deconvolution-based network (DCNN) model for DOA estimation, achieving robustness and accuracy as proven through experiments with simulated and measured data.
This paper proposes a deconvolution-based network (DCNN) model for DOA estimation of direct source and early reflections under reverberant scenarios. Considering that the first-order reflections of the sound source also contain spatial directivity like the direct source, we treat both of them as the sources in the learning process. We use the covariance matrix of high order Ambisonics (HOA) signals in the time domain as the input feature of the network, which is concise while containing precise spatial information under reverberant scenarios. Besides, we use the deconvolution-based network for the spatial pseudo-spectrum (SPS) reconstruction in the 2D polar space, based on which the spatial relationship between elevation and azimuth can be depicted. We have carried out a series of experiments based on simulated and measured data under different reverberant scenarios, which prove the robustness and accuracy of the proposed DCNN model.