Multiple Speech Sources Localization in Room Reverberant Environment Using Spherical Harmonic Sparse Bayesian Learning

摘要

In recent years, sparse representation techniques have been proposed for source localization using spherical microphone arrays (SMAs). However, the performance of these sparse representation techniques for SMAs degrades for speech source localization in the room environment due to sound reverberation. This article proposes a robust sparse presentation method for localization of multiple speech sources in the room environment using an SMA, which employs the spherical harmonic temporal extension of multiple response model sparse Bayesian learning. Real-world experimental results demonstrate that the proposed method outperforms its existing counterparts for speech source localization in the real room environment.