Code
bof/baf/4y/2024/01/1092
Duration
01 January 2024 → 31 December 2025
Funding
Regional and community funding: Special Research Fund
Promotor
Research disciplines
-
Engineering and technology
- Audio and speech processing
- Image and language processing
- Interactive and intelligent systems
- Pattern recognition and neural networks
- Audio and speech computing
Keywords
speech recognition
speech analysis
speaker identification
speech diarisation
speech
Project description
The envisioned core speech technolgies allow both the extraction of verbal information and non-verbal information. The aim of this project 3-fold. First, we want to keep the existing technologies up-to-date. Next, we want to retrain the Flemish (verbal) models based on the latest insights and technologies. Lastly, we want to develop a series of small demos based on the core speech technologies, this both for didactic purposes as well as to attract new (industrial) projects.