Return to Alumni

Israel Dejene Gebru

I am a Ph.D. student within the PERCEPTION team at INRIA Grenoble, advised by Dr. Radu Horaud. My research interests are in audio signal processing, computer vision and machine learning. I am particularly interested in joint processing of audio and visual data for human-robot interaction.

Before starting my Ph.D., I received a B.S. in Computer Engineering from Addis Ababa University in 2008, and a M.S. in Telecommunication Engineering from University of Trento in 2013. I also worked as an engineer at ZTE cooperation from 2009-2011.

I did a six-month research internship at Oculus (Facebook) Research in Pittsburgh.

List of Publications

Journal Articles

  • Gebru, I. D., Silèye Ba, Xiaofei L. & Horaud, R., “Audio-Visual Speaker Diarization Based on Spatiotemporal Bayesian Fusion,” in IEEE TPAMI, (In press, Jan 2017). Research Page

  • Gebru, I. D., Alameda-Pineda, X., Forbes, F., & Horaud, R., “EM algorithms for weighted-data clustering with application to audio-visual scene analysis,” in IEEE TPAMI, (In press, Jan 2016). Research Page

Conference Papers

  • Gebru, I.D., Evers, C., Naylor, P.A., & Horaud, R., “Audio-Visual Tracking by Density Approximation in Sequential Bayesian Filtering Framework” in HSCMA 2017. Best Paper Award Research Page

  • Gebru, I.D., Ba, S., Evangelidis, G. and Horaud, R., “Tracking the Active Speaker Based on a Joint Audio-Visual Observation Model,” in ICCV 2015. Research Page

  • F. Badeig, Q. Pelorson, S. Arias, V. Drouard, I. D. Gebru, X. Li, G. Evangelidis, R. Horaud, “A Distributed Architecture for Interacting with NAO”, in ACM ICMI, 2015 . Research Page

  • Gebru, I. D., Ba, S., Evangelidis, G., & Horaud, R., “Audio-Visual Speech-Turn Detection and Tracking,” in LVA/ICA 2015. Research Page

  • Gebru, I. D., Alameda-Pineda, X., Horaud, R., & Forbes, F., “Audio-visual speaker localization via weighted clustering,” in IEEE MLSP 2014 . Research Page

  • Dang-Nguyen, D.T., Gebru, I.D., Conotter, V., Boato, G. and De Natale, F.G., “Counter-forensics of median filtering,” in IEEE MMSP 2013