Model-based Sparse Component Analysis for Reverberant Speech Localization

This paper proposes a speech localization framework based on model-based sparse recovery. We compare and contrast the computational sparse optimization methods incorporating harmonicity and block structures as well as autoregressive dependencies underlying spectrographic representation of speech signals. Extensive evaluations are conducted to quantify the performance bound for localization of multiple sources from underdetermined mixtures in a reverberant environment. The results demonstrate the effectiveness of sparse Bayesian learning framework for speech source localization. Furthermore, the importance of construction layout of microphone array is investigated. The outcome of this study encourages the use of ad-hoc microphones for the data acquisition set-up.