AI and Automatic Metadata Extraction

AI and Automatic Metadata Extraction (AME) in Production.

Automatic Metadata Extraction (AME) is a key technology needed by modern production systems. AME tools can be used to produce more information (including structured metadata) at a lower cost. Artificial intelligence techniques such as machine learning and deep learning are behind most AME tools. The AME Group is working on different aspects of this domain:

  • tools capabilities and performances,
  • knowledge sharing and facilitating collaboration on AME methods, algorithms and projects,
  • metadata schemas and best practices.


deepl.jpg (Shanghai pudong night scence with neuron deep learning layer...

The EBU X-tagging POC will be shared among group participants. This project aims at developing AI tools to generate high-level tags from the written content. It uses state of the art Natural Language Processing and Machine Learning algorithms. These high-level tags allow assessing the linguistic properties of the written content for fake news detection, authoring, and source of information identification or targeted audience analysis. It can be used, for instance, for recommender systems, content-based search engine, analyse of the posts on social media, asset the properties of articles for journalists among others. If you have data or specific needs on these topics, please contact me.


  • status_med_12px.png Sharing good practices, state of the art and catalogue of AME tools (2021)
  • status_med_12px.png Development ML/DL models for target audience identification (Q1 2021)


  • status_done_12px.png Development of a POC for authorship identification (Q4 2020)
  • status_done_12px.png Development of a POC for fake news detection(Q4 2020)
  • status_done_12px.png Sharing good practices, state of the art and catalogue of AME tools (2020)


Main goal

The EBU AME group is part of the EBU "Metadata and Artificial Intelligence" activities. Its main goal is to help Members adopt and develop AI-based automatic information extraction tools, such as:

  • content tagging for writings, audios and videos,
  • speech-to-text and subtitling,
  • face/voice recognition,
  • location, event and object detection and identification in videos
  • actions detection and identification in videos

Related publications

Related EBU work

The EBU AI Benchmarking project develops tools to evaluate speech-to-text transcription.

The EBU "AI Data Pool" pre-study, which proposes a framework to share resources for training and assessing AI tools.

Related topics