Spanish broadcaster RTVE is working with VSN on a project that uses artificial intelligence to automate metadata content creation from its archive.
The project has been in the testing process for the past four months and will move to a year-long implementation from the end of October.
Files from RTVE’s archive are ingested into VSNExplorer MAM which creates an asset with the media file and an XML file including information about the content provided by the network. Once the content is in the system, the AI engine starts generating the content’s metadata. When the process is over, all the information extracted is displayed in a single and centralised interface.
According to VSN, the process can extract a text transcript from the files in a matter of minutes, while the AI uses facial recognition it the video file and identifies and catalogues the scene, along with the objects, tags, and signs that appear in the footage.
Users can then access all the information required via the VSNExplorer MAM web-based interface and make any required corrections to text etc.
The MAM then creates a number of XML files with all the information which is sent back to the RTVE Archive.
“From a technological point of view, this project was a big challenge for RTVE. For the first time, we deployed a system that allows the content management of our archive using cloud solutions,” stated Carmen Pérez, RTVE deputy director of innovation and technological strategy.
“For the RTVE Documentary Archive, this project not only gives access to thousands of hours of great content, it is also a unique opportunity to influence the development of technologies that will be common in the future. In addition, we are pioneers in the implementation of this technology in the daily workflow of the Archive,” added Virginia Bazán Gil, project manager at RTVE Documentary Archive.