Coronavirus Information for the UC San Diego Community

Our leaders are working closely with federal and state officials to ensure your ongoing safety at the university. Stay up to date with the latest developments. Learn more.

A feedforward neural network for direction-of-arrival estimation

TitleA feedforward neural network for direction-of-arrival estimation
Publication TypeJournal Article
Year of Publication2020
AuthorsOzanich E., Gerstoft P, Niu H.Q
Date Published2020/03
Type of ArticleArticle
ISBN Number0001-4966
Accession NumberWOS:000522971700001
Keywordsacoustic source localization; acoustics; Audiology & Speech-Language Pathology

This paper examines the relationship between conventional beamforming and linear supervised learning, then develops a nonlinear deep feed-forward neural network (FNN) for direction-of-arrival (DOA) estimation. First, conventional beamforming is reformulated as a real-valued, linear inverse problem in the weight space, which is compared to a support vector machine and a linear FNN model. In the linear formulation, DOA is quickly and accurately estimated for a realistic array calibration example. Then, a nonlinear FNN is developed for two-source DOA and for K-source DOA, where K is unknown. Two training methodologies are used: exhaustive training for controlled accuracy and random training for flexibility. The number of FNN model hidden layers, hidden nodes, and activation functions are selected using a hyperparameter search. In plane wave simulations, the 2-source FNN resolved incoherent sources with 1 degrees resolution using a single snapshot, similar to Sparse Bayesian Learning (SBL). With multiple snapshots, K-source FNN achieved resolution and accuracy similar to Multiple Signal Classification and SBL for an unknown number of sources. The practicality of the deep FNN model is demonstrated on Swellex96 experimental data for multiple source DOA on a horizontal acoustic array. (C) 2020 Acoustical Society of America.

Student Publication: 
Research Topics: