MMC Seminar 2025

The programme is now available!

MMC Seminar 2025

Cardiff, Wales – University of South Wales – May 6-8

The programme for the FIAT/IFTA Media Management Seminar 2025 is now available! Join FIAT/IFTA and BBC in Cardiff, Wales, for the 12th edition of FIAT/IFTA’s “Changing Sceneries, Changing Roles” Seminars on media management, metadata, rights, new emerging technologies and changing skillsets.

Gain insights from global experts in the media management field on emerging challenges in the digital archiving and broadcasting sectors. This is an opportunity for professional audiovisual archivists to discover cutting-edge workflows and effective solutions created in response to, and enabled by, emerging AI technology.

More information on registration, topics, sponsors, and accommodation is available on the Seminar’s page.

FIAT/IFTA MEDIA MANAGEMENT SEMINAR 2025

DAY 1 – MAY 7

8:30 AM – 9:30 AM

Registration

9:30 AM – 9:45 AM

Welcome Speeches

9:45 AM – 10:15 AM

Claude AI

By Ludovic Delépine (European Parliament)

Full abstract coming soon.

MMC Seminar 2025

Ludovic Delépine has 30 years of experience in the field of IT, particularly in IT governance in public administration, enterprise architecture, and digital transformation. He is currently Head of the Archives Unit at the Directorate-General of the Presidency. He has also headed the IT Governance Thematic Unit of the Inter-Parliamentary Union for the past seven years. He previously taught computer science at several French universities and was a researcher in CNRS-certified artificial intelligence laboratories.

10:15 AM – 10:45 AM

The AI Sandbox: Driving AI Innovation through Collaborative Intelligence

By Alexandre Rouxel (EBU)

The EBU AI Sandbox is a collaborative environment enabling public service media to explore, test, and refine AI tools specifically tailored to media and archive applications. By connecting AI developers with media and archive professionals, the Sandbox fosters the co-creation of user-centric applications rooted in operational realities. It offers secure, private spaces to evaluate AI using proprietary content while ensuring GDPR compliance and data protection. Grounded in an open-source philosophy, the Sandbox accelerates innovation through transparency, adaptability, and shared learning. Among its flagship projects are a GDPR-compliant facial recognition tool optimised for documentalists and MetaRadio, which transforms linear radio into a rich, searchable experience. The iterative, feedback-based process helps ensure that development efforts are focused on features that add real value to users and fit into their day-to-day workflows. This presentation illustrates how bringing users and developers together can help make AI more valuable and relevant for media archives.

MMC Seminar 2025

Alexandre Rouxel is Senior Project Manager for Data and AI at the European Broadcasting Union (EBU), working within the Technology & Innovation (T&I) department. He supports collaborative initiatives on artificial intelligence and metadata with EBU members – Europe’s public service broadcasters. His work focuses on the development of AI algorithms for media content analysis, tagging and enrichment. He is also responsible for the EBU AI Sandbox, a platform to help members explore, test and evaluate AI tools adapted to media applications. Alexandre is involved in international projects and contributes to standardisation activities, including the SMPTE Task Force on AI and Metadata. Prior to joining the EBU, Alexandre worked for 20 years as an algorithm and systems engineer, contributing to the design of products and technology standards.

10:45 AM – 11:15 AM

Morning Break

11:15 AM – 11:45 AM

The EbuCorePlus ontology as a common language for VRT

By Koen Renders (VRT)

At VRT, like many broadcasting organizations, the production and archiving of diverse media content has led to the existence of multiple systems with complex integrations. This often results in various “dialects” created by operational teams or the tools themselves. Archives, in particular, which import data from different systems and have their own archiving systems, suffer from different understandings and policies in the operational units. VRT Archive has been searching for a solution in the form of a “common language” to improve data exchange between systems and facilitate migrations. The EbuCorePlus ontology, which offers a semantic framework for describing processes and content in the broadcast world, seems to be the most evident standard to start with. This talk will describe our goals, planning, and experiences so far in this journey.

MMC Seminar 2025

Koen Renders has been working at the VRT archives for 25 years, mainly in the field of music. A few years ago he joined the Archive Data Team, focusing on general metadata modeling and ontology.

11:45 AM – 12:15 PM

Where do your pixels come from? Reliable media provenance to reduce disinformation risks

By Charlie Halford (BBC)

AI involvement in media creation and editing is now commonplace, and humans are unable to reliably discern AI generated media from that which is captured with a camera. We will examine the different places where AI and other, less advanced editing techniques have the potential to harm, and how the BBC R&D has co-developed the “Content Credentials” technical specification to help address them. We’ll cover the transparent disclosure of the “ingredients” and “actions” involved in producing media, and how we identify whether AI has been used. We’ll look at the different uses of media provenance: capture and ingest, storage and retrieval, and how consumers might make use of this extra information.

MMC Seminar 2025

Charlie Halford is a Principal Research Engineer in the BBC’s Research & Development department, where he works as part of the Advisory Team, which does longer term technology and media industry trend forecasting and analysis and produces technical strategy recommendations for the rest of the BBC. As part of this, he leads the BBC’s work on “Project Origin”, a technical standard co-founded and developed by the BBC that seeks to address the dangers of disinformation on the internet by providing secure media provenance. His background is in software engineering and architecture, where he has spent a significant proportion of his career working with content management and publishing technologies. At the BBC, he has been lucky enough to combine that expertise with a love for citizen empowerment and public service journalism.

12:15 PM – 1:00 PM

Sponsors Session

By FAST FORWARD, MAYAM, OMNISEARCH, SDVI, VIZRT

MMC Seminar 2025
Mayam
MMC Seminar 2025
MMC Seminar 2025
MMC Seminar 2025

1:00 PM – 2:00 PM

Lunch

2:00 PM – 2:30 PM

Easier Comprehension of Archive Items with Automated Content Summaries

By Lauri Saarikoski and Ronja Halte (YLE)

This presentation takes you through the development of automated content summaries done by the radio archive team at Yle, the Finnish Broadcasting Company. Building on our previous work in speech recognition, during 2024 we focused on creating content summaries from transcripts, aiming for high automation levels and backwards compatible metadata. We would like to share, from a practical perspective, what we have learned on topics such as comparing different LLMs and their parameters, building prompts, and deciding on what the summaries should look like. For broader context, the presentation also provides an update on current AI-related topics and plans at Yle Archives, and how projects such as this can be shared with and adopted by other teams.

MMC Seminar 2025
MMC Seminar 2025

Lauri Saarikoski serves as Development Manager for the Archives at Yle, the Finnish Broadcasting Company. He provides expert support to various archive teams in such areas as operational and technical planning, strategy, cross-functional collaboration and management. With over 15 years of experience in music and media archive work, he specialises in metadata, AI and innovation activities. He actively participates in the EBU and FIAT/IFTA communities and currently focuses on media-related AI applications, process development and data economy.

Ronja Halter is an Archive Editor in the Radio Archive Team at Yle, the Finnish Broadcasting Company. With a background in language and literature studies, as well as computer science, she is enthusiastic about combining her knowledge of both humanities and technology in her work. She has been building contemporary solutions for media archive work by implementing automated and AI-assisted workflows for metadata management and creation. Outside of work, Ronja enjoys knitting, video games, and cuddling up with her two cats.

2:30 PM – 3:00 PM

Projects and Implementations of Machine-Learning and AI at the ORF

By Gerhard Stanz (ORF)

The presentation will show how innovative tools are implemented into archival user interfaces at the ORF. The examples will be out of all stages between prototype and productive use. From a more generalized perspective there will be an insight how the Company learns about the potentials of AI by use of the AIditor an award winning AI-Framework available to all ORF users.

MMC Seminar 2025

Gerhard Stanz works at the Multimedial Archive of the ORF (Austrian Broadcasting Cooperation). He started his career as a Television Archivists in all the classical job-roles of archiving, documenting, researching in – as well as creating content out of – archive material. The informatization of the media business led him to his current job-role as “Systems Developer”. In this position he acts as an intermediary between the technical departement and archive users in operating, maintaining, troubleshooting,testing and further developing the it-infrastructure of the archive. His main responsibility at the ORF is the file-archive.

3:00 PM – 3:30 PM

INA IA’s project overview / Transcription and named entity focus / Semantic search

By Olivio Segura (INA)

Full abstract coming soon.

MMC Seminar 2025

Graduated in audiovisual & heritage management after studying movies and visual arts, Olivio Segura joined INA’s Collection Management Department in 2019, assigned to an experimental and cross-departmental mission focus on experimenting AI-based solutions. Working alongside data scientists from the Information System Division, trained to machine learning models management, he contributed to develop automatic segmentation and indexing process for TV contents in charge of change management. Since 2020 Olivio joined the Data Department service as a project manager to pursue the lead and coordination of various AI projects.

3:30 PM – 4:00 PM

Afternoon Break

4:00 PM – 4:30 PM

Metadata Generation in the AI Era: Multi-label Indexing for More Efficient News Production

By Yuki Yasuda (NHK)

Broadcast media organisations produce many news scripts every day for dissemination as content. Such text data is often reused in the process of producing TV programmes and web news. To efficiently utilise this large volume of data, it is necessary to accurately attach metadata such as topic labels that indicate the contents of the text. However, manually assigning metadata takes an enormous amount of time and effort. With the aim of reducing costs, we developed a system that automatically adds metadata to news articles. The system provides a variety of metadata, such as labels, keywords, auto-generated titles, emotion tags and speculative location when a news article is input. We focused on topic labels since they are versatile when used as metadata. We proposed a novel loss function that utilises weighting and a label smoothing technique to suppress label imbalance. Experimental results show that our method outperforms baselines.

MMC Seminar 2025

Yuki Yasuda received the B. H. and M. H. degrees in Human Science from Waseda University in 2015 and 2017 respectively. He joined NHK (Japan Broadcasting Corporation) in 2017, and since 2019 has been working at the Science and Technology Research Laboratories, where he is developing technology to support production work by applying natural language processing. Currently he is working on multi-label classification of news articles and has developed an automatic labelling system. The system was introduced at IBC2024 and was selected for “The best of IET and IBC 2024.”

4:30 PM – 5:00 PM

AI techniques in a collaborative setting, applied to the case of regional broadcasters

By Miel Vander Sande (meemoo)

Meemoo, the Flemish institute for archives, digitises and preserves a large amount of primarily audiovisual objects from organisations in the cultural heritage, media and government sector. More than 8 million items are currently archived, including newspapers, images, video, and audio files. Besides archiving, meemoo also tends the distribution of material to specific target groups via web platforms, including education and the general public. Behind those platforms, there’s a vast amount of metadata that is collected from our partners, which enables the archive material to be searchable and usable across the various collections.

The amount of audiovisual objects has long exceeded the available, often manually created metadata. Hence, we turn to artificial intelligence to enable the automatic annotation of audio and video at scale, which is the goal of the SharedAI project: a collaboration between meemoo, regional broadcasters and public broadcaster VRT. We were able to produce transcripts for and identify public figures and locations in numerous hours of content by applying a combination of face-recognition, speech-to-text and Named-Entity Recognition (NER).

In this presentation, we will talk about the approach and results of the SharedAI project. We also zoom in on how the output of our automatic annotation pipelines were integrated with the archive’s metadata in our Knowledge Graph, which is our uniform and application-independent access to metadata. Lastly, we will discuss how we collaboratively construct a thesaurus of public figures in Flanders targeted at face recognition software and integrate with other knowledge graphs.

MMC Seminar 2025

Miel Vander Sande is Data Architect at meemoo, Flemish Institute for Archives. Meemoo manages a large quantity of mainly audio-visual material from more than 160 partners in cultural heritage and media. More than 8 million objects are currently stored, ranging from digitised newspapers, photos, video, and audio. As a Data Architect, Miel is responsible for the organisation, quality, and usability of metadata, both today and tomorrow. Miel has a background in Web technology, a PhD in publishing Linked Data and leads the Knowledge Graph project, which unifies all metadata used within meemoo.

5:00 PM – 5:30 PM

Panel

More information on this panel will be available soon.

FIAT/IFTA MEDIA MANAGEMENT SEMINAR 2025

DAY 2 – MAY 8

9:30 AM – 10:00 AM

Developing Language Technologies for the Welsh language

By Gruffudd Prys (Bangor University)

Tasked by the Welsh Government to develop a foundation of Language Technology resources for the Welsh language, the Language Technologies Unit at Bangor University has developed a range of technologies aimed at facilitating the use of Welsh in digital environments. These include bilingual speech recognition models, a number of different synthetic voices and domain-specific machine translation engines as well as finetuning commercial and open source AI models. This presentation will provide an overview of the available technologies, and demonstrate their use within: Macsen, an Alexa-like app for Welsh; Trawsgrifiwr, a subtitling website; and Trosleisio, a service for adding synthesized Welsh-language voiceovers to videos. Finally, some of the challenges facing improving such models and making them available under open-source licenses will be discussed.

MMC Seminar 2025

Gruffudd Prys is the Head of the Language Technologies Unit at Bangor University, a multidisciplinary team of 8 linguists and 5 software developers specializing in the creation of Welsh language resources for the digital age. Having worked as a terminologist developing technical terms for Welsh-medium education, Gruff ventured into the field of Natural Language Processing (NLP), developing part-of-speech taggers and named entity recognition models for Welsh. Currently he leads a Welsh Government funded project sourcing Welsh-language data in the form of speech and text to enable the creation of open source language models, open datasets and associated resources to create a strong foundation of language technologies for Welsh.

10:00 AM – 10:30 AM

Reviving Ireland’s Linguistic Legacy: A Groundbreaking Digital Preservation of Irish Dialects

By Anja Mahler (RTÉ) & Brian Ó Raghallaigh (Dublin City University)

This presentation, co-presented by RTÉ and Dublin City University, explores a pioneering effort to digitally preserve and analyse Ireland’s rich linguistic heritage. With over a century’s worth of broadcast recordings, the project leverages advanced digitization and linguistic research, unlocking a vast dataset for scholars, educators, and the wider public. Attendees will gain insights into the methodologies, discoveries, and future applications of this vital resource, now publicly accessible via the dialect repository Canúint.ie.

MMC Seminar 2025
MMC Seminar 2025

Anja Mahler is the Senior Archivist for Sound at Radió Teilifis Éireann (RTÉ), Ireland’s national public service broadcaster. She oversees the digitization of RTÉ’s audio archive, which includes quarter-inch tapes and optical disc media, to ensure the preservation of Ireland’s audio heritage for future generations. With over a decade of experience in audio-visual and digital preservation, Anja has held roles at the IFI Irish Film Archive and the Digital Repository of Ireland. She brings expertise in archival workflows, media archaeology, metadata standards, and sustainable preservation strategies that are internationally recognized.

Dr Brian Ó Raghallaigh is an Assistant Professor at Dublin City University (DCU), where he is a member of the Gaois research group. He is Principal Investigator (PI) on the Placenames Database of Ireland project and Co-Investigator (Co-I) on the Canúint project. He has a BA (Mod.) in computer science, linguistics and Irish, and a PhD in speech technology, both from Trinity College Dublin. His current research is focused on the creation of digital Irish-language resources for general and specialist users, language technology and other applications. He is a Board Member of the Digital Repository of Ireland (DRI).

10:30 AM – 11:00 AM

Could AI Save Gaelic? Language Technology, Big Tech and the Future of Minority Languages

By William Lamb (University of Edinburgh)

The future of Gaelic, like many minority languages, is uncertain. Could language technology help secure its survival? While AI systems like ChatGPT now permit real-time English interactions, achieving this for Gaelic is challenging. This lecture examines key technological advances needed to bridge this gap and their impact on language revitalisation. Research at the University of Edinburgh explores two promising solutions to data scarcity in low-resource languages: speech recognition and synthetic data augmentation using Large Language Models. A key approach involves leveraging archival data to develop language technology and then using technology to annotate and enhance archival materials, creating a virtuous circle of resource expansion. However, technological progress also raises concerns, particularly in collaborations between major tech companies and minority language communities, where issues of data ownership and cultural preservation must be carefully managed.

MMC Seminar 2025

Prof William Lamb (University of Edinburgh) holds a Personal Chair in Gaelic Ethnology and Linguistics. Since joining the University in 2010, Professor Lamb has made significant contributions to Gaelic dialectology, oral tradition and language technology. He is the author of Scottish Gaelic: A Comprehensive Grammar (Routledge, 2024) and has published extensively in peer-reviewed venues on Digital Humanities topics. Lamb recently completed an MSc in Speech and Language Processing (UoE) with distinction and, over the past 5 years, has secured substantial grants from the Arts and Humanities Research Council (AHRC) and other funders focusing on Digital Humanities and Artificial Intelligence. Outwith his academic role, Professor Lamb serves on the Board of Management for Faclair na Gàidhlig and several other executive committees dedicated to Gaelic language and culture. He is also a Fellow of the Generative Artificial Intelligence Laboratory (GAIL) and an Affiliate of the Edinburgh Futures Institute (EFI).

11:00 AM – 11:30 AM

Morning Break

11:30 AM – 12:00 PM

Using IA for pre-indexation of the EBU EVN items

By Janique Sonderegger & Laurent Guignard (RTS)

How we use a LLM through an internal portal to help us to write headlines and summaries of agency items, based on their scripts. We keep the datas safe and we we save time to do work with greater added value.

MMC Seminar 2025
MMC Seminar 2025

Janique Sonderegger is a documentalist and specialist in new information technologies and data management. She participate in the implementation of new AI tools at the RTS and in the business analysis around these developments.

Laurent Guignard is a documentalist at RTS from 1995. He’s a specialist in Sport and Information material. He’s been Team Manager from 2005.

12:00 PM – 12:30 PM

AI image recognition and breaking point detection

By Emanuele Balossino & Davide Zampatti (Mediaset)

Full abstract coming soon.

MMC Seminar 2025

Full bio coming soon.

12:30 PM – 1:00 PM

ChatGPT in Archives: Hype or Valuable Tool?

By Martijn van der Vliet (Sound & Vision)

Sound & Vision started to experience with ChatGPT and its potential in archives management several years ago and presented about this on the World Conference in 2023. At the ingest department, experiments were conducted to summarize speech-to-text data and generate a starting point for descriptions of websites or games. Another experiment involved creating simple Python scripts using ChatGPT’s assistance for automating basic archival tasks such as MD5 checksum validation, reading media files, generating file lists, and renaming files.

What happened since those early days, did the archive embed these kind of practices in its daily practices or not?”

MMC Seminar 2025

Martijn van der Vliet has been working at the Netherlands Institute for Sound & Vision for over 8 years. For the past year, he has served as coordinator of the digitisation department. In this role, he is responsible for managing the digitisation team, consisting of 10 staff members, as well as a 2-person depot management team. Together, they ensure the smooth intake, processing, and preservation of audiovisual materials.

Martijn brings expertise in digital ingest and preservation workflows, focusing on maintaining high standards in the handling and long-term management of digital assets. Given the wide variety of material sources, he continuously works on optimising and adapting workflows to meet evolving needs, actively exploring the use of AI-driven solutions to improve efficiency.

1:00 PM – 2:00 PM

Lunch

2:00 PM – 2:30 PM

Accessing our Audiovisual History: A Small Country in a Changing World

By Einion Gruffudd (National Library of Wales)

This talk will describe how the National Library of Wales established a National Broadcast Archive, with support from the National Lottery Heritage Fund and the Welsh Government, and is now a host to most of Wales’ audiovisual history incuding BBC, ITV and S4C content. This project is in its final stages and has vastly improved access to this audiovisual material and also provided a springboard for developing access to other audiovisual content in the Library. The Screen and Sound team must now face new challenges in terms of technology, resources, rights, the material which is waiting to be collected, and new expectations from audiences. The team’s adoption of AI technologies features the need to support the Welsh language, and also the development of practical solutions with support from a collaborative project involving Kings University London, the BFI and other audiovisual archives in the UK.

MMC Seminar 2025

Einion started his career as a video librarian at Barcud television resources company in north Wales, before returning to Aberystwyth in 1992 to work at the National Library of Wales where he has served in the Manuscripts, IT and Unique Collections departments. His work has included managing Library systems, business continuity, setting up NLW’s digital archive, and successfully leading a HLF funded project to digitise all 1,200 tithe maps of Wales. Since 2017 he has been the manager of a NLHF project to establish a National Broadcast Archive at the National Library of Wales, and is also now the manager of the Screen and Sound section at the Library.

2:30 PM – 3:00 PM

Supporting the BBC Archives with AI: Unlocking Discovery, Accessibility, and Preservation

By Ross Wilson (BBC)

The BBC’s archives hold decades of invaluable content but making it discoverable and reusable at scale is a significant challenge. This talk explores how AI-driven content enrichment can transform discovery and reuse workflows whilst keeping humans in the loop. We’ll examine approaches such as speech-to-text for indexing, face and object detection for tagging, and scene segmentation for improved navigation. Through real-world examples—like uncovering hidden interviews via transcripts and automating rights management with OCR—we’ll highlight how AI can be used to enhance accessibility, streamline workflows, and support editorial decision-making. Join us to explore how AI is being harnessed to support the BBC Library, unlocking new opportunities for discovery and reuse.

MMC Seminar 2025

Ross Wilson is a Lead Technical Architect in the BBC’s Archives Technology & Services department. The department manages one of the world’s largest multimedia archives with a mission to safeguard the BBC’s archives now and for the future. Over nearly a decade, Ross has worked with multiple teams across the organisation, experiencing the breadth of the media supply chain. He has a software engineering background, having worked on the BBC websites, iPlayer, mobile apps, and BBC Account – which enables a more personalised signed-in BBC for audiences. Now he’s leading the architectural direction of the new BBC Library, a new platform to support content discovery and reuse.

3:00 PM – 3:30 PM

How the Next-Gen AV Archivist is Taking Off: ATRESMEDIA Keeps Evolving

By Pilar Auseron Marruedo

Technology is not only a tool—it’s a driver of transformation. In audiovisual information management, long based on human expertise, the arrival of algorithms marked a turning point. After an initial phase centered on automatic transcription and facial recognition, ATRESMEDIA’s Archive is now embracing generative AI.

This shift goes beyond innovation; it’s reshaping the identity of the audiovisual archivist. The next-gen professional is emerging as a hybrid: combining archival know-how with data skills, capable of supervising AI processes, ensuring metadata quality, and maximizing content value.

This evolution supports a larger goal: to redefine the archivist’s role as a key player in the content production ecosystem. At ATRESMEDIA, we strongly believe that the future of audiovisual archiving lies in professionals ready to collaborate with machines, shape new narratives, and actively contribute to the digital transformation of the media industry.

MMC Seminar 2025

Pilar Auserón Marruedo is a senior Media Archive Specialist at ATRESMEDIA, where she has developed her career in audiovisual documentation and content management. She specialized in the integration of metadata and artificial intelligence tools into archive workflows. Her work focuses on improving access, searchability, and the editorial use of audiovisual archives across multiple platforms. Pilar has played an active role in transforming the traditional role of the documentalist into a more dynamic, cross-functional profile, contributing to innovation in content generation and data-driven storytelling. She is particularly interested in the intersection between language, technology, and media, and in how these elements shape the future of archival work.

3:30 PM – 4:00 PM

Afternoon Break

4:00 PM – 4:30 PM

Learning how to Fly – Humans and AI, the Learning Curve

By René Duursma (Groningen Archives)

The Learning Curve: How the Groningen Archives leverage seminars like MMC to achieve great things in their relatively small (regional) archive. Why knowledge sharing is crucial and can be truly inspirational is illustrated through the experience of the Groningen Archives, where they have developed their own approach to incorporating humans into the loop of AI-generated metadata — with accuracy monitored by a dedicated group of volunteers. The Groningen Archives house the sound and video archives of both the local broadcaster (OOG TV) and the regional broadcaster (RTV Noord). These valuable collections form the foundation for the Ai metadata project called ‘The Sound of Groningen’.

MMC Seminar 2025

René Duursma has been Curator of Audiovisual Materials at the Groningen Archives since 2005. Leading a small team of five people and a group of volunteers, he is dedicated to the ongoing digitization and metadata management of the collection. Duursma is constantly involved in projects aimed at the general public, often in collaboration with partner organizations. He is a member of the Domain Council (AVA_NET) and serves as the Chairman of NORAA (Regional Archives in the Netherlands). In addition to his work at the archive, Duursma is a musician (Kinetophone), filmmaker, and presenter.

4:30 PM – 5:00 PM

Panel

More information on this panel will be available soon.

5:00 PM – 5:10 PM

Wrap Up

LATEST NEWS

LATEST NEWS