Intuitive spoken dialogues are a prerequisite for human-robot inter-
action. In many practical situations, robots must be able to identify
and focus on sources of interest in the presence of interfering speak-
ers. Techniques such as spatial filtering and blind source separa-
tion are therefore often used, but rely on accurate knowledge of the
source location. In practice, sound emitted in enclosed environments
is subject to reverberation and noise. Hence, sound source localiza-
tion must be robust to both diffuse noise due to late reverberation, as
well as spurious detections due to early reflections. For improved
robustness against reverberation, this paper proposes a novel ap-
proach for sound source tracking that constructively exploits the spa-
tial diversity of a microphone array installed in a moving robot. In
previous work, we developed speaker localization approaches using
expectation-maximization (EM) approaches and using Bayesian ap-
proaches. In this paper we propose to combine the EM and Bayesian
approach in one framework for improved robustness against rever-
beration and noise.