@Article{cmc.2020.09848,
AUTHOR = {Xiaoyan Zhao, Shuwen Chen, Lin Zhou, Ying Chen},
TITLE = {Sound Source Localization Based on SRP-PHAT Spatial Spectrum and Deep Neural Network},
JOURNAL = {Computers, Materials \& Continua},
VOLUME = {64},
YEAR = {2020},
NUMBER = {1},
PAGES = {253--271},
URL = {http://www.techscience.com/cmc/v64n1/39141},
ISSN = {1546-2226},
ABSTRACT = {Microphone array-based sound source localization (SSL) is a challenging task 
in adverse acoustic scenarios. To address this, a novel SSL algorithm based on deep 
neural network (DNN) using steered response power-phase transform (SRP-PHAT) 
spatial spectrum as input feature is presented in this paper. Since the SRP-PHAT spatial 
power spectrum contains spatial location information, it is adopted as the input feature for 
sound source localization. DNN is exploited to extract the efficient location information
from SRP-PHAT spatial power spectrum due to its advantage on extracting high-level 
features. SRP-PHAT at each steering position within a frame is arranged into a vector, 
which is treated as DNN input. A DNN model which can map the SRP-PHAT spatial 
spectrum to the azimuth of sound source is learned from the training signals. The azimuth 
of sound source is estimated through trained DNN model from the testing signals. 
Experiment results demonstrate that the proposed algorithm significantly improves 
localization performance whether the training and testing condition setup are the same or 
not, and is more robust to noise and reverberation.},
DOI = {10.32604/cmc.2020.09848}
}