Research

Engin Erzin is a member of the Multimedia, Vision, and Graphics Laboratory (MVGL), where he is actively part of many national and international research projects.

Engin Erzin’s area of expertise is multimedia signal processing, including speech and audiovisual signal processing, human-computer interaction, and pattern recognition. He focuses on various signal processing and statistical machine learning techniques to study correlations, dependencies, and independencies across modalities, which are loosely synchronous such as speech and gestures, speech and emotion, or strongly synchronous such as acoustic and throat microphone recordings, music, and dance.

Current & Recent Projects

  1. E. Erzin, Y. Yemez, T.M. Sezgin, ”Backchannel Feedback Modeling for Human-Computer Interaction,” funded by TUBITAK, 2018- 2020.
  2. E. Erzin, ”Use of Transfer Learning on Multimodal Analysis of Speech,” funded by TUBITAK, 2018- 2019.
  3. E. Erzin, “Gaussian Mixture Model based Discriminative Classifier Design for Speaker Recognition,” funded by TUBITAK, 2016-2017.
  4. E. Erzin, Y. Yemez ”JESTKOD: Multimodal Analysis and Modeling of Human Body Gestures and Speech under Affective and Interactive Communication Scenarios,” funded by TUBITAK, 2013- 2016.
  5. T.M. Sezgin, Y. Yemez, E. Erzin, ”JOKe and Empathy of a Robot/ECA: Towards social and affective relations with a robot (JOKER),” funded by FP7-CHISTERA, 2013-2016.
  6. E. Erzin, Y. Yemez, A.M. Tekalp, ”Speech Driven Upper Body Animation,” funded by Turk Telekom, 2010-2012.
  7. E. Erzin, Y. Yemez, A.M. Tekalp, ”COST ACTION 2102: Cross Modal Analysis of Verbal and Nonverbal Communication,” funded by TUBITAK & COST, 2008-2010.
  8. E. Erzin, ”Joint Processing of Throat-, Bone- and Acoustic-Microphone Recordings for Robust Speech Recognition,” funded by TUBITAK, 2005-2008.
  9. E. Erzin, Y. Yemez, A.M. Tekalp, ”NEDO Project: International Research Coordination of Driving Behavior Signal Processing based on Large Scale Real World Database,” funded by Japanese Government, 2005-2007.
  10. E. Erzin, A. M. Tekalp, Y. Yemez, ”DRIVE-SAFE: Signal Processing and Advance Information Technologies for Improving Driver/Driving Prudence and Accident Reduction,” funded by DPT, 2005-2007.
  11. A. M. Tekalp, E. Erzin, Y. Yemez, “SIMILAR: The European taskforce creating human-machine interfaces SIMILAR to human-human communication,” FP6 Network of Excellence, 2003-2007.
  12. E. Erzin,  A. E. Cetin, K. Oflazer and H. Erdogan, “COST 278: Spoken Language Interactions in Telecommunications,” funded by TUBITAK, March 2002 – March 2006.
  13. A. M. Tekalp, E. Erzin, and Y. Yemez, “Multi-Stage and Multi-Modal Signal Processing for Person Identification,” funded by TUBITAK, March 2002 – March 2004.