VESTA (VidEo: Système de Traitement d’Annotation) [VidEo: Annotation Processing System] project focuses on developing and deploying an integrated set of innovative computer tools for analyzing and annotating audio and video recordings.
The project targets the educational studies research community that is interested in knowledge acquisition and technology-based approaches to learning. These researchers regularly record students as they perform various learning tasks. The recordings are then reviewed many times to identify certain elements of interest regarding student motivation, understanding, and behaviours. Analyzing the recordings is an extremely lengthy and painstaking process that is subject to misinterpretation.
The VESTA project will provide researchers with tools that will significantly accelerate, and in some cases automate, the analysis and annotation of recordings. These tools include face recognition, speaker detection and assisted transcription of conversations. The coding associated with this analysis can be shared among researchers, supporting increased cooperation and opening the door to larger-scale multi-partner studies. Analysis components can be reused to design new data processing chains.
The project should result in considerable gains in productivity by significantly reducing analysis time while improving consistency. Researchers will be able to conduct their experiments more quickly and accelerate the transfer of their most promising results to educational institutions, thereby helping to improve training of Canada’s workforce.