Auditory-Visual Speech Processing (AVSP) 2011

Volterra, Italy
September 1-2, 2011

Auditory and Photo-realistic Audiovisual Speech Synthesis for Dutch

Wesley Mattheyses, Lukas Latacz, Werner Verhelst

Vrije Universiteit Brussel, Dept. ETRO-DSSP, Interdisciplinary Institute for Broadband Technology IBBT, Brussels, Belgium

Both auditory and audiovisual speech synthesis have been the subject of many research projects throughout the years. Unfortunately, in recent years only very few research focuses on synthesis for the Dutch language. Especially for audiovisual synthesis, hardly any available system or resource can be found. In this paper we describe the creation of a new extensive Dutch speech database, containing audiovisual recordings of a single speaker. The database is constructed as such that it can be employed in both auditory and audiovisual speech synthesis systems. Subsequently, we describe how we achieve high-quality auditory speech synthesis by applying the database in our textto- speech framework. In addition, it is explained how we used the new database to attain photorealistic audiovisual text-tospeech synthesis for Dutch. The new database and its applications for synthesis are a significant addition to the resources for Dutch speech synthesis research.

Index Terms. Dutch speech database, speech synthesis, audiovisual speech synthesis

Full Paper

Bibliographic reference.  Mattheyses, Wesley / Latacz, Lukas / Verhelst, Werner (2011): "Auditory and photo-realistic audiovisual speech synthesis for Dutch", In AVSP-2011, 55-60.