Section: New Results

Simultaneous sound-source separation and localization

Human-robot communication is often faced with the difficult problem of interpreting ambiguous auditory data. For example, the acoustic signals perceived by a humanoid with its on-board microphones contain a mix of sounds such as speech, music, electronic devices, all in the presence of attenuation and reverberations. We proposed a novel method, based on a generative probabilistic model and on active binaural hearing, allowing a robot to robustly perform sound-source separation and localization. We show how interaural spectral cues can be used within a constrained mixture model specifically designed to capture the richness of the data gathered with two microphones mounted onto a human-like artificial head. We describe in detail a novel expectation-maximization (EM) algorithm that alternates between separation and localization, we analyze its initialization, speed of convergence and complexity, and we assess its performance with both simulated and real data. Subsequently, we studied the binaural manifold, i.e., the low-dimensional space of sound-source locations embedded in the high-dimensional space of perceived interaural spectral features, and we provided a method for mapping interaural cues onto source locations. See [21] , [12] . A journal paper was submitted in 2013 and accepted with minor revisions.