Multiple acoustic source localization using deep data association

• Published in: Applied acoustics Vol. 192; p. 108731
• Main Authors: Ayub, Muhammad Saad, Jianfeng, Chen, Zaman, Anam
• Format: Journal Article
• Language: English
• Published: Elsevier Ltd 01.04.2022
• Subjects: Acoustic sensor network; Acoustic signals; Data association; Deep neural network; Location estimation; Long short time memory (LSTM); Location estimation; Deep neural network; Acoustic signals; Long short time memory (LSTM); Acoustic sensor network; Data association
• ISSN: 0003-682X; 1872-910X
• DOI: 10.1016/j.apacoust.2022.108731

[Display omitted] •Multiplex dynamic LSTM based data association for DOA-based multiple acoustic source localization.•Computationally efficient data association among DOAs in a distributed acoustic sensor network.•Performance analysis on urban sounds in various simulations and real-life experiments.•Improved accuracy in comparison to present data association-based source localization methods. Acoustic source localization is a key component of the various acoustic monitoring systems. In this paper, we address the data association problem occurring in the localization of multiple acoustic sources for a distributed acoustic sensor network. The direction of arrival (DOA) of multiple signals is computed at each node and forwarded to a central system for localization. A challenging problem known as data association occurs because DOAs received from different nodes belonging to the same acoustic source are not known. In a realistic environment, the complexity of the data association method increases with the increase in the number of array nodes and sources. With the increase in complexity, the time required for estimating the location of all the sources also increases. Time-critical scenarios of acoustic monitoring require the location to be estimated as close to real-time as possible. To overcome this problem a data-driven deep learning-based solution is presented to control the complexity of the system. A learning approach that formulates the data association among DOAs as combinatorial optimization is proposed. Firstly, features are extracted along with the DOAs of every detected source at each node in the network. Subsequently, a dynamic multiplex Long Short-term memory(LSTM) network is formulated to estimate the association probabilities of the DOAs from different nodes. The methodology is tested using simulations and real data experiments. Comparative analysis is done to validate that the methodology achieves higher association and localization accuracy with a reduced computational time as compared to present state-of-the-art methods.