A Deep Network for Single-Snapshot Direction of Arrival Estimation

This paper examines a deep feedforward network for beam-forming with the single-snapshot sample covariance matrix (SCM). The conventional beamforming formulation, typically quadratic in the complex weight space, is reformulated as real and linear in the weight covariance and SCM. The reformulated SCMs are used as input to a deep feed-forward neural network (FNN) for two source localization. Simulations demonstrate the effect of source incoherence and performance in a noisy tracking example. The FNN beamformer is experimentally tested on the Swellex96 experiment S95 source tow with a loud interferer.

[1]  Peter Gerstoft,et al.  Source localization in an ocean waveguide using supervised machine learning , 2017, The Journal of the Acoustical Society of America.

[2]  Peter Gerstoft,et al.  Ship localization in Santa Barbara Channel using machine learning classifiers. , 2017, The Journal of the Acoustical Society of America.

[3]  Piya Pal,et al.  Sparse Bayesian learning for beamforming using sparse linear arrays. , 2018, The Journal of the Acoustical Society of America.

[4]  Soumitro Chakrabarty,et al.  Multi-Speaker DOA Estimation Using Deep Convolutional Networks Trained With Noise Signals , 2018, IEEE Journal of Selected Topics in Signal Processing.

[5]  W S Hodgkiss,et al.  Matched field processing with data-derived modes. , 2001, The Journal of the Acoustical Society of America.

[6]  Christoph F. Mecklenbräuker,et al.  Multisnapshot Sparse Bayesian Learning for DOA , 2016, IEEE Signal Processing Letters.

[7]  Peter Gerstoft,et al.  Adaptive and compressive matched field processing. , 2017, The Journal of the Acoustical Society of America.

[8]  Bhaskar D. Rao,et al.  An Empirical Bayesian Strategy for Solving the Simultaneous Sparse Approximation Problem , 2007, IEEE Transactions on Signal Processing.

[9]  Peter Gerstoft,et al.  An Overview of Sequential Bayesian Filtering in Ocean Acoustics , 2011, IEEE Journal of Oceanic Engineering.

[10]  Haizhou Li,et al.  A learning-based approach to direction of arrival estimation in noisy and reverberant environments , 2015, 2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[11]  Carlos Fernandez-Granda,et al.  A Learning-based Framework for Line-spectra Super-resolution , 2018, ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[12]  Guigang Zhang,et al.  Deep Learning , 2016, Int. J. Semantic Comput..

[13]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[14]  William S. Hodgkiss,et al.  Mirages in shallow water matched‐field processing , 1995 .