TV Speech-to-Text: New report in Panorama Audiovisual about À Punt-MLLP project on computer-assisted subtitling for live and pre-recorded broadcast media

Online magazine Panorama Audiovisual recently published a report with up-to-date information on the R&D project by the Valencian public broadcaster À Punt and the Universitat Politècnica de València’s VRAIN-MLLP research group in which streaming and offline speech-to-text are being applied for computer-assisted subtitling of live and pre-recorded broadcast media.

On 6 October 2020, the public broadcaster of the region of València À Punt and Universitat Politècnica de València (UPV) signed an agreement for real-time computer assisted subtitling of audiovisual contents based on artificial intelligence. In this first year of the agreement, the MLLP research group, part of the UPV’s VRAIN Institut Valencià d’Investigació en Intel·ligència Artificial, have deployed their streaming and offline speech-to-text technology (1st place in the IberSpeech-RTVE 2020 TV Speech-to-Text Challenge) in À Punt for the computer-assisted subtitling of À Punt’s live and pre-recorded broadcast contents.

On 2 December 2021, online magazine Panorama Audiovisual published a report with up-to-date information on the status of this project so far: “À Punt y MLLP (Universitat Politècnica de València): ¿el proyecto definitivo de transcripción automatizada?” (in Spanish).

Based in Madrid, Spain, Panorama Audiovisual is an online trade magazine covering since 2009 the latest developments in the broadcast and cinema industries, focusing on Spain and Latin America.

We recommend reading this report (in Spanish) to learn more about how À Punt and the UPV’s VRAIN-MLLP research group are collaborating in applying state-of-the-art live speech-to-text technology with the goal of being able to subtitle 100% of À Punt’s broadcast contents to improve their accessibility.

Posted in All, Projects and tagged , , , .