Indoor Sound Source Localization with Probabilistic Neural Network
This addresses robust localization for indoor applications like smart homes or surveillance, but appears incremental as it builds on existing probabilistic neural network methods.
The paper tackles indoor sound source localization in adverse environments like high reverberation and low SNR by proposing the Generalized cross correlation Classification Algorithm (GCA), achieving average azimuth and elevation angle errors of 4.6 and 3.1 degrees respectively.
It is known that adverse environments such as high reverberation and low signal-to-noise ratio (SNR) pose a great challenge to indoor sound source localization. To address this challenge, in this paper, we propose a sound source localization algorithm based on probabilistic neural network, namely Generalized cross correlation Classification Algorithm (GCA). Experimental results for adverse environments with high reverberation time T60 up to 600ms and low SNR such as -10dB show that, the average azimuth angle error and elevation angle error by GCA are only 4.6 degrees and 3.1 degrees respectively. Compared with three recently published algorithms, GCA has increased the success rate on direction of arrival estimation significantly with good robustness to environmental changes. These results show that the proposed GCA can localize accurately and robustly for diverse indoor applications where the site acoustic features can be studied prior to the localization stage.