Project

Language and speech technological tools for cutch as web services in a workflow (TTNWW)

Duration
01 January 2010 → 30 September 2012
Funding
Regional and community funding: various
Research disciplines
  • Natural sciences
    • Artificial intelligence
  • Social sciences
    • Cognitive science and intelligent systems
  • Engineering and technology
    • Modelling
    • Biological system engineering
    • Signal processing
Keywords
audio signal processing speaker identification language identification
 
Project description

This project is part of the Flemish/Dutch collaboration within the pan European infrastructure creating Common Language Resources ans Technology infrastructure (CLARIN). It is a collaboration between the universities of Leuven, Ghent and Antwerp and it development of a service that can index audio in terms of speech technology part. Within the latter, the Ugent is responsible for the development of a service that can index audio in terms of speech/non-speech, gender of the speeker, identity of the speeker, language of the speech, meaning of the non-speech (e.g. applause, jingle, laughter, etc.).