Artificial intelligence applications in media archives
DOI:
https://doi.org/10.3145/epi.2023.sep.17Keywords:
Artificial intelligence, AI, Media archives, Television archives, Audiovisual archives, Audiovisual documentation, Speech technologies, Natural language processing, Metadata, Media, Radio, Television, FIAT/IFTAAbstract
The aim of this paper is to present an international overview of the use of artificial intelligence in the context of media archives in broadcasters, preservation institutions and press agencies, through a comprehensive analysis of sources primarily focusing on case studies presented at international conferences and seminars, together with the results of the survey on the use of artificial intelligence conducted by FIAT/IFTA. Once the most commonly used technologies have been defined and we have identified the stages of the production workflow in which they are used, we will discuss the specific applications of these technologies in television archives, audiovisual heritage preservation organisations, press agencies and innovation projects where technology vendors and media companies collaborate. Finally, we will deal with the challenges related to the implementation of AI in media archives, the need for datasets in the development of language models, and the relevance of a sensible use of technology.Â
Downloads
References
AI4Media (2023). The AI4Media project. https://www.ai4media.eu
Aragón Noticias (2021). "Aragón TV participa en la prueba piloto de una herramienta de inteligencia artificial". Aragón noticias, 13 noviembre. https://www.cartv.es/aragonnoticias/sociedad/aragon-tv-participa-en-la-prueba-piloto-de-una-herramienta-de-inteligencia-artificial-6130
í…strand, Mikaela; Stí¥hl, Sally (2023). "Finding without tagging: AI experiments for improved findability in the new media archive at SVT". In: EBU Data technology seminar 2023. https://tech.ebu.ch/publications/ai-experiments-for-improved-findability-in-the-svt-media-archive
Bailer, Wermer; Bauer, Christoph; Rottermanner, Gernot (2021). "Analysing used needs for automatic metadata creation and advanced search in the Tailored Media Project". In: EBU MDN workshop 2021. https://tech.ebu.ch/publications/analysing-user-needs-for-automatic-metadata-creation-and-advanced-search-in-the-tailored-media-project
Battrick, Kathey (2022). "Case study: AI indexing. Assessing and selecting AI services". In: FIAT/IFTA world conference: Archive out of the box! https://fiatiftaworldconference2022.sched.com/event/149Cd
Battrick, Kathey; Petitpont, Frederic (2022). "How Asharq News is leveraging multimodal AI indexing with Newsbridge: Inside the back-end, operational & technical workflows of a multilingual news channel". In: FIAT/IFTA world conference: Archive out of the box! https://fiatifta.org/world-conference-2022-recordings-available
BBC (2018a). AI TV on BBC 4.1: BBC Four is giving an AI control of your TV for two nights. https://www.bbc.co.uk/programmes/p06jrfcc
BBC (2018b). Made by machine: When AI met the archive. BBC Four. https://www.bbc.co.uk/programmes/b0bhwk3p
Berger, Jake; Armstrong, Andy (2022). "BBC radio news scripts 1937-1995: Using an automated tagger to enable journeys across time and space". In: EBU MDN workshop 2022. https://tech.ebu.ch/publications/bbc-radio-news-scripts-1937--1995-using-an-automated-tagger-to-enable-journeys-across-time-and-space
Bouchet, Leonard; Ducret, Sebastien (2019). "A visual feature extraction pipeline and its applications for radio television Suisse". In: Proceedings of the FIAT/IFTA media management seminars. Changing sceneries, changing roles, part IX, pp. 51-59. https://fiatifta.org/library/proceedings-of-the-fiat-ifta-media-management-seminars
Bruccoleri, Angelo; Iacoviello, Roberto; Messina, Alberto; Metta, Sabino; Montagnuolo, Maurizio; Negro, Fulvio (2022). AI in vision: High quality video production & content automation. RAI. Radiotelevisione Italiana. Centre for Research, Technological Innovation and Experimentation. AI4media. https://www.ai4media.eu/whitepapers/ai-in-vision-high-quality-video-production-content-automation
Cátedra RTVE Universidad de Zaragoza (2017). https://catedrartve.unizar.es
Coppejans, Charlotte (2021). How artificial intelligence slashes editing time for Associated Press (AP). https://www.limecraft.com/how-the-associated-press-is-using-ai-to-create-automated-shot-lists
Couteux, Anne; Segura, Olivio (2023). "News channel automatic segmentation". In: FIAT/IFTA media management seminar 2023. https://fiatifta.org/seminar/media-management-seminar-2023
Daniels, Marijin (2023). "Metadata enrichment using lower third character recognition". In: FIAT/IFTA media management seminar 2023. https://fiatifta.org/seminar/media-management-seminar-2023
Daniels, Marijn; Degryse, Jasper (2021). "How VRT automated the segmentation of programmes with AI". In: EBU MDN workshop 2021. https://tech.ebu.ch/publications/how-vrt-automated-the-segmentation-of-programs-with-ai
FIAT/IFTA (2022). Archive Achivement Awards 2022. https://fiatifta.org/awards-2022
FIAT/IFTA (2023). AI Survey. The results are now available. https://fiatifta.org/ai-survey-results
FIAT/IFTA Media Management Commission (2013). Proceedings of the FIAT/IFTA media management seminars. Changing sceneries, changing roles. Part VI. Metadata as the cornerstone of digital archiving. https://fiatifta.org/library/proceedings-of-the-fiat-ifta-media-management-seminars
FIAT/IFTA Media Management Commission (2017). Proceedings of the FIAT/IFTA media management seminars. Changing sceneries, changing roles. Part VIII. Embracing automation - enhancing discoverability. https://fiatifta.org/library/proceedings-of-the-fiat-ifta-media-management-seminars
FIAT/IFTA Media Management Commission (2019). Proceedings of the FIAT/IFTA media management seminars. Changing sceneries, changing roles. Part IX. Game changers? From automanation to curation - Futureproofing AV content. https://fiatifta.org/library/proceedings-of-the-fiat-ifta-media-management-seminars
FIAT/IFTA Media Management Commission (2023). MMC Seminar. Download the slides. https://fiatifta.org/mmc-seminar-2023-download-the-slides
Fí¶rster, Constantin (2023). "Generation of training data for landmark recognition in videos using named entity recognition". In: EBU data technology seminar 2023. https://tech.ebu.ch/publications/landmarkner--generating-training-data-for-landmark-recognition
Ghanbari, Shirin (2022). "Strategy and challenges for developing AI applications". In: EBU AIM community meeting 2022.
Green, Eva-Lis; Gupta, Jacqui (2019). "20 year of MMC seminars: changing sceneries, changing roles 1998-2019". In: Proceedings of the FIAT/IFTA media management seminars. Changing sceneries, changing roles, part IX, pp. 7-17. https://fiatifta.org/library/proceedings-of-the-fiat-ifta-media-management-seminars
INA (2023a). International affairs. Institut National de l´Audiovisuel. https://www.ina.fr/institut-national-audiovisuel/international-affairs
INA (2023b). Collection, preservation, and documentation of audiovisual heritage. Institut National de l´Audiovisuel. https://www.ina.fr/institut-national-audiovisuel/collection-preservation-and-documentation-of-audiovisual-heritage
Lewis, Michelle; Jarret, Nicholas (2023). Explore how Europeana Subtitled increased access to audiovisual heritage. https://pro.europeana.eu/post/explore-how-europeana-subtitled-increased-access-to-audiovisual-heritage
Lleida-Solano, Eduardo; Ortega-Giménez, Alfonso; Miguel, Antonio; Bazán-Gil, Virginia; Pérez-Cernuda, Carmen; De-Prada, Alberto (2022). RTVE 2018, 2020 and 2022 database description. http://catedrartve.unizar.es/reto2022/RTVE2022DB.pdf
López-de-Quintana, Eugenio (2021). AI algorithms for media cataloguing in Atresmedia Group. https://fiatifta.org/awards-2021
López-de-Quintana, Eugenio; León-Carpio, Antonio (2021). "Artificial intelligence for a role change in television archives: The Atresmedia-Etiqmedia experience". Journal of digital media management, v. 10 n. 2, pp. 177-187. http://etiqmedia.com/ficheros/JDMM_10_2_JDMM0006_e_lopez_de_quintana_and_carpio-1.pdf
Manders, Tim (2019). "Harder, better, faster, stronger: Adding face recognition in the mix at NISV". In: FIAT/IFTA world conference: AV archives in the all-media world. https://fiatifta2019.sched.com/event/S0Sa/harder-better-faster-stronger-adding-face-recognitionin-the-mix-at-nisv
Manders, Tim (2022). "Face recognition at the Netherlands Institute for Sound and Vision. Is it really harder, better, faster, stronger". In: FIAT/IFTA media management seminar. https://fiatifta.org/seminar/media-management-webinars-2022-2
Manders, Tim; Wigham, Marie (2021). "More metadata, lots of links, but what do you do with them? Practical examples of the added value of automatic metadata and linked data for archive users". In: 2021 FIAT/IFTA world conference. Advancing the digital dividend.
Martin, Camille; Segura, Olivio (2021). "Using AI tools to segment and describe broadcast live stream. In: EBU MDN workshop 2021. https://tech.ebu.ch/publications/using-ai-tools-to-segment-and-describe-broadcast-livestream
Messina, Alberto (2021). "Enabling AI with dataset engineering". In: EBU MDN workshop 2021. https://tech.ebu.ch/publications/enabling-ai-with-dataset-engineering
Messina, Alberto; Montagnuolo, Maurizio (2023). "Integrating open knowledge-bases and AI-tools". In: EBU data technology seminar 2023. https://tech.ebu.ch/publications/integrating-open-knowledge-bases-and-ai-tools
Microsoft (2023). Azure cognitive services documentation. https://learn.microsoft.com/en-us/azure/cognitive-services
Mí¼hling, Markus; Korfhage, Nikolaus; Pustu-Iren, Kader; Bars, Joanna; Knapp, Mario; Bellafkir, Hicham; Vogelbacher, Markus; Schneider, Daniel; Hí¶rth, Angelika; Ewerth, Ralph; Freisleben, Bernd (2022). "VIVA: visual information retrieval in video archives". International journal on digital libraries, v. 23, n. 4, pp. 319-333. https://doi.org/10.1007/s00799-022-00337-y
Netherlands Institute for Sound and Vision (2023). Mission and vision. https://www.beeldengeluid.nl/en/about/mission-and-vision
Open AI (2022). Introducing ChatGPT. https://openai.com/blog/chatgpt
Open AI (2023). Dalle-E 2. https://openai.com/dall-e-2
Parmentier, Matthieu (2021). "The challenge of data management and governance". In: EBU MDN workshop 2021. https://tech.ebu.ch/publications/governance-of-data-at-ftv-for-better-usage-and-valorisation-of-the-programs
Petit, Thomas (2022). "Facial recognition: Trombinos". En: FIAT/IFTA media management seminar. https://www.youtube.com/watch?v=qM10EXb6988
Reuters (2023). Automated transcription, translation and identification. https://liaison.reuters.com/help/reutersconnect#automated-transcription-translation-and-identification
Reuters Staff (2020). Reuters applies AI technology to 100 years of archive video to enable faster discovery, supported by Google DNI. https://www.reuters.com/article/rpb-lavita-video-archive/reuters-applies-ai-technology-to-100years-of-archive-video-to-enable-faster-discovery-supported-by-google-dni-idUSKCN2591VO
Rezzonico, Pietro (2020). "AI-based tools to help archive workflows". In: EBU tech roundtable on archives 2020. https://tech.ebu.ch/publications/presentations/roundtable_2020_archive_workflows/RTS-archive_tools
Roche-Dioré, Axel (2023). "data.ina.fr a portal to promote media analytics". In: EBU data technology seminar 2023. https://tech.ebu.ch/publications/datainafr--a-portal-to-promote-media-analytics
RTVE (2021). Metadatado automático de contenidos del Fondo Documental de RTVE. https://licitaciones.rtve.es/licitacion/licitaciones/detalle?id=1208797
RTVE (2023). Metadatado automático de contenidos del Fondo Documental RTVE https://licitaciones.rtve.es/licitacion/licitaciones/detalle?id=2200005
Sánchez-García, Pilar; Merayo-Álvarez, Noemí; Calvo-Barbero, Carla; Diez-Gracia, Alba (2023). "Spanish technological development of artificial intelligence applied to journalism: companies and tools for documentation, production and distribution of information". Profesional de la información, v. 32, n. 2. https://doi.org/10.3145/epi.2023.mar.08
Schreiber, Jonas (2022). "AI going local - conception and training of specialized Bavarian´ AI models at Bayerischer Rundfunk". In: EBU AI-AME 2022.
Selkí¤lí¤, Elina (2017). "Heading for AI". In: Proceedings of the FIAT/IFTA media management seminars. Changing sceneries, changing roles, part VIII. Embracing automation - Enhancing discoverability, pp. 169-189. https://fiatifta.org/library/proceedings-of-the-fiat-ifta-media-management-seminars
Sonderegger, Janique (2023). "Speaker recognition service: Roles and expectations". In: FIAT/IFTA media management seminar. https://fiatifta.org/seminar/media-management-seminar-2023
Speechmatics (2023). The most accurate speech to text API. https://www.speechmatics.com
Startfruit Tagger (2023). BBC Startfruit tagger. http://starfruit.virt.ch.bbc.co.uk/#
Steskal, Lubos (2023). "Using free-text queries to perform visual search in video archives". In: EBU data technology seminar 2023. https://tech.ebu.ch/publications/using-free-text-queries-to-perform-visual-search-in-video-archive
Tverberg, Are (2021). "TV 2 Norway´s AI hub and QA Monitor: A gateway to ASR services for a low-resource language". In: EBU MDN workshop 2021. https://tech.ebu.ch/publications/tv-2-ai-hub-and-qa-monitor--a-gateway-to-asr-services-for-a-low-resource-language
Verwaest, Maarten (2022). "Using AI for automatic shot listing in news at Associated Press". In: EBU MDN workshop 2022. https://tech.ebu.ch/publications/using-ai-for-automatic-shot-listing-in-news---the-associated-press
Viljanen, Kim (2022). "Content tagging in Yle Areena: Improving quality and process". In: EBU MDN workshop, 2022. https://tech.ebu.ch/publications/content-tagging-in-yle-areena---improving-quality-and-process
Wenger-Glemser, Gabriele (2019). "Shaping the future Artificial Intelligence in AV archives". In: Proceedings of the FIAT/IFTA media management seminars. Changing sceneries, changing roles, part IX. pp. 61-78. https://fiatifta.org/library/proceedings-of-the-fiat-ifta-media-management-seminars
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2023 Profesional de la información
This work is licensed under a Creative Commons Attribution 4.0 International License.
Dissemination conditions of the articles once they are published
Authors can freely disseminate their articles on websites, social networks and repositories
However, the following conditions must be respected:
- Only the editorial version should be made public. Please do not publish preprints, postprints or proofs.
- Along with this copy, a specific mention of the publication in which the text has appeared must be included, also adding a clickable link to the URL: http://www.profesionaldelainformacion.com
- Only the final editorial version should be made public. Please do not publish preprints, postprints or proofs.
- Along with that copy, a specific mention of the publication in which the text has appeared must be included, also adding a clickable link to the URL: http://revista.profesionaldelainformacion.com
Profesional de la información journal offers the articles in open access with a Creative Commons BY license.