TTNWW: Language and Speech Tools for Dutch as Webservice in a Workflow

Period:

01/03/2010 - 30/09/2012

Partners:

Katholieke Universiteit Leuven
Universiteit Gent
Universiteit Antwerpen
KADOC (Leuven)
Radboud Universiteit (Nijmegen, the Netherlands)
Universiteit Twente (Enschede, the Netherlands)
Aletta (Amsterdam, the Netherlands)
Meertens Instituut (Amsterdam, the Netherlands)

Funding:

EWI Vlaanderen

Promoter:

Patrick Wambacq

Co-promoters:

Frank Van Eynde (CCL, K.U.Leuven)

Objectives:

The main target of the Speech-part of the TTNWW-project is to create an easy to use, distributed speech recognition platform for non HLT-experts who do not have any background knowledge of speech recognition. It is our intention, once the project is up-and-running, to place the speech recognition platform at one of the official CLARIN-centres. The distributed speech recognition platform must help the researchers from the humanities with: a) solving their research questions and b) defining new research questions. The distributed nature of the project makes it possible to easily change/replace existing recognition tools with better ones without the need building (and distributing) new software programs. The CLARIN-compatibility of both tools and data guarantees a smooth working of the program (no need to constantly change the input/output of the tools and restructure the data).