Roeland J.F. Ordelman

Roeland Ordelman is an expert in speech technology, audiovisual access technology and cross-media search & recommendation concepts. He has a background in research, audiovisual archiving and industry, and is a well-experienced project manager and team leader.

He received his PhD in 2003 on the use of speech recognition technology to improve access to audiovisual archives and worked on a wide range of national and international projects in the area of multimedia retrieval. He has been involved in organizing benchmark evaluations in the MediaEval Benchmark Evaluation Series and  TRECVid. His current work focuses on multimedia research infrastructures (Digital Humanities and Social Sciences), multimedia content-based recommendation, speech-based human-robot interaction and spoken conversational search. In collaboration with the Netherlands Institute for Sound and Vision, he coordinates 'Living Labs' around topics in Media Innovation and Museum Interaction, that involve industry, research and user communities for mutual benefit.

At the Netherlands Institute for Sound and Vision, one of the largest audiovisual archives in Europe that also holds a Museum, his work focuses on innovative products that can be brought from R&D into production, either at the institute or related areas. 

• Speech Technology (spoken conversational search, speech-based robot interaction)
• Multimedia Retrieval & Recommendation
• Multimedia Research Infrastructures (Digital Humanities & Social Sciences)

• Speech processing
• Advanced speech processing

• CLARIAH-PLUS (2019-2023)
• CLARIAH-CORE (2014-2018)
• FP7-AXES (2011-2015)
• Verteld Verleden
• COMMIT
• FP6 Media Campaign (2006-2008)
• FP6 MESH (2006-2009)
• NWO CHORAL (2006-2012)
• NWO CATCH(PLUS) (2004-2012)
• FP6 AMIDA (2006-2009)
• FP6 AMI (2003-2006)
• FP5 ECHO (2002-2004)
• MultimediaN (2000-2003)
• Waterland (2000)
• DRUID (1998-2000) -- Document Retrieval Using Intelligent Disclosure. My first project during my PhD research focussing on speech recognition as a tool for audiovisual search. The project description: "Retrieval of information from large text corpora has become a mature science in the last years. Nowadays one can search for information with "natural" question phrases which will result in lists of documents that deal with the relevant topic, also if they do not literally contain the words of the query. What remains a problem, though, is that much of the relevant information is not available in a written format, but only as sound (speech) or image. In order to make this information retrievable, audio and/or video fragments have to be transformed into some kind of textual representation, for example using automatic speech recognition. This transformation is the central topic of the DRUID project