Dr.-Ing. Michael Feld (Project Leader)

Dr. Michael Feld is a senior researcher at the German Research Institute for Artificial Intelligence (DFKI). He is currently leading the research project MADMACS, as well as co-leading the project HySociaTea. His research focus is on multimodal interaction and dialogue, personalization of human-machine interfaces involving user modelling and user adaptation, and speech technologies such as speech dialogue systems and speech-based classification. He also has a background in pattern classification / machine learning. He received his PhD supervised by Prof. Wolfgang Wahlster in 2011 on the topic “A Speaker Classification Framework for Non-intrusive User Modeling: Speech-based Personalization of In-Car Services“. Further research interests include application architecture design, home automation, parallel programming, and mobile devices.

Michael joined DFKI in early 2005. After finishing his Diploma thesis in Computer Science at Saarland University in 2006, he became a full-time researcher in the Intelligent User Interfaces (IUI) department headed by Prof. Wolfgang Wahlster. Since then, he has been involved in several projects working in key areas such as automotive user interfaces, speech technologies and speaker classification, personalization, smart energy, and mobile devices. The most notable work was done in projects COLLATE, CARMINA, and SiAM. Other projects he has been working on include COLLATE, SBC, NetShield, EMERGENT, HEMS, and GetHomeSafe. Between 2009 and 2015, Michael was a member of the Automotive IUI group at DFKI lead by Dr. Christian Müller. He has also been part of the Chair of Prof. Wahlster, teaching and assisting with lectures and seminars until today.

In the field of speaker classification, Michael has been working closely together with Dr. Christian Müller. One of his main accomplishments was the design and development of a complete framework for all tasks related to speech-based classification supporting specialized algorithms, strict resource requirements and flexible deployment. His PhD thesis (graded Magna Cum Laude) follows up closely in on this, using the architecture to explore new methods that produce even better classification results. The results were subsequently used in multiple projects.

Contact: michael.feld at dfki . de


Please refer to the list of publications.