Deleforge A, Horaud R (2012)
Publication Language: English
Publication Type: Conference contribution
Publication year: 2012
ISBN: 978-1-4673-1026-0
DOI: 10.1109/MLSP.2012.6349784
The problem of 2D sound-source localization based on a robotic binaural setup and audio-motor learning is addressed. We first introduce a methodology to experimentally verify the existence of a locally-linear bijective mapping between sound-source positions and high-dimensional interaural data, using manifold learning. Based on this local linearity assumption, we propose an novel method, namely probabilistic piecewise affine regression, that learns the localization-to-interaural mapping and its inverse. We show that our method outperforms two state-of-the art mapping methods, and allows to achieve accurate 2D localization of natural sounds from real world binaural recordings.
APA:
Deleforge, A., & Horaud, R. (2012). 2D sound-source localization on the binaural manifold. In Proceedings of the IEEE International Workshop on Machine Learning for Signal Processing (MLSP), 2012. Santander, ES.
MLA:
Deleforge, Antoine, and Radu Horaud. "2D sound-source localization on the binaural manifold." Proceedings of the IEEE International Workshop on Machine Learning for Signal Processing (MLSP), 2012, Santander 2012.
BibTeX: Download