Spanish public broadcaster Radio Televisión Española (RTVE) has been working with VSN on a project for automated metadata creation of content from the network’s archive through artificial intelligence tools.
It is applying AI to 11,000 hours of content from its archive, including material produced in the 1960s and 1970s, using the cloud service VSNExplorer MAM along with an AI engine from Etiqmedia.
The VSNExplorer MAM is central to RTVE’s new project
Following four months of testing, the one-year project started in October, with files from the archive ingested in VSNExplorer MAM. The system creates a previous asset with the media file and an XML file with information about the content provided by the network. Then the AI engine starts generating metadata. All the information extracted is then displayed in a single, centralised interface.
Connect with VSN on IBC Digital
For audio, the technology can retrieve a complete text transcription in just a few minutes, including recognition of people, places, events, products, organisations and dates that are mentioned, creating an automated catalogue of the content and keywords. For video, it has facial recognition and identifies the scene, along with objects, tags and signs that appear.
Virginia Bazán Gil, project manager, RTVE Documentary Archive, said: “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.”
RTVE is also using VSNExplorer MAM for a new Innovation Hub project that is studying the use of cloud-based tools to create news content in small news production centres.