Matesub is a web-based tool released by Translated that combines state-of-the-art AI with a WYSIWYG (What You See Is What You Get) editor for supporting professionals in the creation of subtitles for audio visual documents. Matesub generates subtitling suggestions through a processing pipeline which concatenates three main modules, based on neural models: an automatic speech recognition system, a text segmenter and a neural machine translation system. Matedub is the Matesub twin which supports the professional dubbing of audio visual documents.
The development of Matesub and Matedub was funded by the European Institute of Innovation and Technology (EIT), a body of the European Union, through the MateDub (2020) and MateDub++ (2021) projects. Within them, the FBK’s MT research unit helped build the automatic subtitling chain.