Pavel Korshunov

Short Biography

Pavel Korshunov is a postdoctoral researcher in Biometrics group (head of the group: Dr. Sébastien Marcel) at Idiap Research Institute (Martigny, Switzerland), currently working on the problem of speaker anti-spoofing detection. Originally from Saint-Petersburg, Russia, he received his Ph.D. in Computer Science from School of Computing, National University of Singapore (advisor: Dr. Wei Tsang Ooi) in 2011 and was a postdoctoral researcher in MMSPG (head of the group: Dr. Touradj Ebrahimi) at EPFL (Lausanne, Switzerland) from 2011 till 2015. He is a recipient of ACM TOMM Nicolas D. Georganas Best Paper Award in 2011, two top 10% best paper awards in MMSP 2014, and top 10% best paper award in ICIP 2014. He has over 70 research publications, and he is a co-editor of the JPEG XT standard for HDR images. His research interests span several areas, including deepfakes and their detection, audio visual tampering dtection, age verification, video analysis, quality assessment, crowdsourcing, high dynamic range imaging, privacy protection, and, also lately, speech analysis, speaker recognition, speaker anti-spoofing, and machine learning. He is one of the current contributors to the signal processing and machine learning open source toolbox Bob.

Education

  • PhD, Computer Science, advisor: Wei Tsang Ooi, National University of Singapore, from Aug 2003 till Apr 2011
  • Specialist, Mathematics, advisor: Koznov D. V., St. Petersburg State University, Russia, from Sep, 1997 till July 2002

Professional Experience

  • Dolby Inc. (USA). Evaluated the perfromance of Dolby's 'Pulsar' HDR monitor prototype (May 2015-Jul 2015).
  • iCelero (USA). As a leader of three person team, developed a prototype of H.264 video transcoder (May 2011-Sep 2011).
  • FXPAL (USA). Developed a web-based video presentation capturing system (Jun 2007-Dec 2007).
  • Lanit-Tercom (Russia). As a member of a team, an in-house UML-based modelling tool (a year of work in 2000-2002).

Awards (selected)

  • Best paper award in ICML 2019 workshop "Synthetic Realities: Deep Learning for Detecting AudioVisual Fakes"
  • ACM TOMM Nicolas D. Georganas Best Paper Award for a journal paper in 2011
  • One top 10% paper in ICIP 2014 conference and two top 10% papers in MMSP 2014 conference.

Main Publications (selected from more than 70)

  • Pavel Korshunov and Sebastien Marcel. Vulnerability assessment and detection of deepfake videos. In International Conference on Biometrics (ICB 2019), Crete, Greece, June 2019.
  • Pavel Korshunov and Sebastien Marcel. Subjective and objective evaluation of deepfake videos. In IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2021.
  • Pavel Korshunov and Sebastien Marcel. Impact of score fusion on voice biometrics and presentation attack detection in cross-database evaluations. IEEE Journal of Selected Topics in Signal Processing, June 2017.
  • A. Artusi, R. Mantiuk, T. Richter, P. Korshunov and P. Hanhart et al. JPEG XT: A Compression Standard for HDR and WCG Images. in IEEE Signal Processing Magazine, 2016.
  • Using Face Morphing to Protect Privacy P. Korshunov and T. Ebrahimi. IEEE International Conference on Advanced Video and Signal-Based Surveillance (AVSS), Poland, Aug 2013.
  • Video Quality for Face Detection, Recognition and Tracking P. Korshunov and W. T. Ooi. ACM Transactions on Multimedia Computing, Communications, and Applications (TOMM), Nicolas D. Georganas Best Paper Award of 2011.

Contact

Please drop me an email at pavel.korshunov@idiap.ch

Tel: +41 27 721 7756
Office: 207.1-7
Contact