A Least Squares Narrowband DOA Estimator with Robustness Against Phase Wrapping
Tobias Kabzinski, Emanuël A. P. Habets · 2019
Narrowband direction-of-arrival (DOA) estimates are commonly used for source localization, parametric spatial audio coding, and directional filtering. As previously shown, a linear least squares direction estimate can be obtained by minimizing the difference of expected and observed inter-microphone phase differences. In this work, it is shown that phase wrapping induces severe estimation errors especially at frequencies just below spatial aliasing frequencies and in low signal-to-noise ratios. A cost function to mitigate the influence of phase wrapping errors on the DOA estimation is proposed. Even though the proposed cost function is nonlinear, it is shown that one iteration of a gradient descent method with proper initialization provides a large improvement when compared to the linear least squares solution.