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.
2022
Sharing good practices, state of the art and catalogue of AME tools
2021
- Sharing good practices, state of the art and catalogue of AME tools
- Development and deployment of an AI-based Fake News Detector
- Supervision of a Master Thesis on Unsupervised Video Summarization
2020
- Development of a POC for authorship identification (Q4 2020)
- Development of a POC for fake news detection(Q4 2020)
- 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.