Microphone Array Signal Processing for Robot Audition

Heinrich Löllmann (1) , Alastair Moore (2) , Patrick Naylor (2) , Boaz Rafaely (3) , Radu Horaud (4) , Alexandre Mazel (5) , Walter Kellermann (1)

1 FAU - Friedrich-Alexander Universität Erlangen-Nürnberg = University of Erlangen-Nuremberg
2 DEEE - Department of Electrical and Electronic Engineering [London]
3 Department of Electrical and Computer Engineering [Beer-Sheva]
4 PERCEPTION - Interpretation and Modelling of Images and Videos
5 Aldebaran Robotics [Paris]

Robot audition for humanoid robots interacting naturally with humans in an unconstrained real-world environment is a hitherto unsolved challenge. The recorded microphone signals are usually distorted by background and interfering noise sources (speakers) as well as room reverberation. In addition, the movements of a robot and its actuators cause ego-noise which degrades the recorded signals significantly. The movement of the robot body and its head also complicates the detection and tracking of the desired, possibly moving , sound sources of interest. This paper presents an overview of the concepts in microphone array processing for robot audition and some recent achievements.

Mots clés: ego-noise suppression; microphone array processing; robot audition; humanoid robots; source tracking

Domaines: Traitement du signal et de l'image [eess.SP]; Son [cs.SD]

Heinrich Löllmann, Alastair Moore, Patrick Naylor, Boaz Rafaely, Radu Horaud, et al.. Microphone Array Signal Processing for Robot Audition. IEEE Workshop on Hands-free Speech Communication and Microphone Arrays, IEEE Signal Processing Society, Mar 2017, San Francisco, United States. pp.51-55, ⟨10.1109/HSCMA.2017.7895560⟩. ⟨hal-01485322⟩