Link to ANU Homepage


College of Engineering and Computer Science
Research School of Information Sciences and Engineering
Australian National University, Canberra

If you are interested in the Audio-Video Australian English Speech Data Corpus AVOZES, click the link on the left or here.

Prospective Students

Interested research students (PhD, Masters, Honours) feel free to email me. Click here or on 'Students' on the left for more information.
Recording sample data
(Photo: ANU Reporter vol 30 issue 7)

Research Interests

My research interests can largely be summarised as being in vision for HCI and related signal processing areas:

Current Work

A Brief Biography

Download my CV

Since December 2008, I am employed as a Research Fellow at Faculty of Information Sciences and Engineering, University of Canberra where my research focus continues to be in the areas of face and facial feature tracking and its applications, and more geneally in Computer Vision, Affective Computing and Multimodal Human-Computer Interaction. I am also holding an adjunct research fellow position with the Department of Information Engineering of the Research School of Information Sciences and Engineering (RSISE) at the Australian National University (ANU). I was an elected executive member of the Australian Speech Science and Technology Association (ASSTA) from December 2004 until September 2008. I am a member of the Human Communication Sciences Network (HCSNet), an ARC research network bringing together researchers and other interested parties on how humans communicate with each other and with computers. It was established in January 2005 for 5 years. I am also a member of the IEEE (Computer Society, Signal Processing Society), the International Speech Communication Association (ISCA), and the Australian Pattern Recognition Society.

Before joining the University of Canberra, I was a Senior Research Scientist at Seeing Machines since April 2007, an innovative computer vision company in Canberra, developing cutting edge face tracking technology, such as faceLAB and faceAPI. Before that, I was a Researcher at the Vision Science, Technology and Applications (VISTA) program of National ICT Australia (NICTA) since May 2004. I was involved in the driver assistance systems project "Smart Cars" and in the "Spectral Imaging and Source Mapping (SISM)" project which investigates the use of camera systems beyond the visible spectrum (near and far infrared, UV). Prior to that, I worked for 2 years as a research fellow in the Department of Human Centered Interaction Technologies at the Fraunhofer Institute for Computer Graphics in Rostock, Germany. I was involved as scientific project leader in the face:)me and the eNoteHistory projects. Face:)me is concerned with the visual tracking of facial features and the recognition of a user's affective state ('emotions') from these features. ENoteHistory is novel project aiming at computer-aided scribe identification of 18th century music scores.

I did my PhD studies at the Research School of Information Sciences and Engineering (RSISE) at the Australian National University (ANU) from 1998 until 2002 in the area of Audio-Video Speech Processing (AVSP) (also known as Auditory-Visual or Audio-Visual Speech Processing), for which I was awarded the ASSTA PhD of The Year Award 2004. The PhD project was concerned with the development of a real-time stereo-vision lip tracking algorithm and an investigation of the statistical relationship of audio and video speech parameters on the example of Australian English. My supervisors were Dr Bruce Millar, Professor Alex Zelinsky, and Dr Jordi Robert-Ribes. For publications in this area, please have a look at my list of publications.

Earlier, I had graduated in Computer Science (German degree Diplom-Informatiker, equivalent to a Master's degree) at the Department of Computer Science at the University of Rostock (Germany) in January 1998. I did my Master's thesis at the Philips Research Laboratories in Hamburg. Within my studies I specialised in Computer Graphics with particular interests in medical image processing, computer vision, scientific visualization, and geometric modelling.

Author: Roland Göcke
E-Mail: Roland.Goecke @

Last modified: Thu Jul 15 10:19:16 AUS Eastern Normalzeit 2010