PSM are facing the need to raise the quantity and the quality of content they create to address linear and non-linear channels. To do so, they are adopting agile technologies to accelerate the production and the management of massive amounts of data. The three pillars of these evolutions are data management, computing architectures and machine learning. EBU groups are addressing these three pillars by providing:
- Development of open source tools;
- Development of good practices and standards;
- Dissemination.
Groups
The umbrella group that oversees the work in the Metadata and AI domain, maximizing knowledge sharing and collaboration. This group meets monthly.
Media Cloud Microservice Architecture (MCMA)
MCMA is a serverless/micro-services strategy for media. It aims to help developers to move to "Function as a Service" architectures. This project provides open-source libraries. Standardization of MCMA has started with SMPTE.
The EBU and several Members have created and continue to develop a tool for benchmarking machine learning-based Speech-To-Text (STT) systems. This open-source tool can be integrated into production workflows.
The main activity of this group is to support Members in the domain of metadata, which plays an essential role in media. To do so, the group develops specifications and promotes innovation, such as the use of semantic technologies.
AI and Automatic Metadata Extraction
Work addressed in this group includes metadata schemas, the capabilities and performance of automatic metadata extraction tools, and the development of machine learning algorithms and related tools.
Communities
This community organizes the annual MDN Workshop for developers to share knowledge, learn from their peers, obtain feedback and collaborate on metadata-related and AI projects. The topics cover EBU Data & AI activities, metadata, machine learning and data processing architectures.
Currently the following deliverables are planned (green indicates the deliverable has already been delivered). Note that deliverables are dependent on enough participation in the work and that the planning is subject to change. New deliverables are added regularly.
2021
Launch control: a web-based application to monitor and deploy complex cloud infrastructure (Q1 2021)
MAM based on MCMA (Q1 2021)
Cloud agnostic engine to develop workflows (Q2 2021)
Open-source libraries on GitHub for AWS, Azure, GCP (Q4 2021)
Containers management and standardised workflow integration (Q4 2021)
Standardisation at SMPTE (Q4 2021)
Sharing good practices, state of the art and catalogue of AME tools (Q4 2021)
Development of AI models for audience identification for written content (Q1 2021)
2020
Google platform development and integration in front-end (Q1 2020)
MCMA Developers Workshop @ Bloomberg (USA) (Q1 2020)
Code factorisation of FFMPEG and STT benchmarking (Q1 2020)
Presentation and demonstrations at EBU PTS 2019 (Q1 2020)
Add the Levenshtein distance to the STT benchmarking code (Q1 2020)
Test the first STT benchmarking software release with the three metrics (Q1 2020)
Test the STT benchmarking API and Docker image (Q1 2020)
Study on action detection and identification (Q1 2020)
Study on fake news detection (Q1 2020)
Publish STT benchmarking release 1.0.0 on PyPi (Q2 2020)
Update the STT benchmarking documentation on ReadTheDocs (Q2 2020)
EBUCore 1.10 - EBU Tech 3393 (Q2 2020)
CCDM 2.2 - EBU Tech 3351 (Q2 2020)
MDN Workshop 2020 (Q3 2020)
Study on action detection and identification (Q1 2020)
Study on fake news detection (Q1 2020)
Development of AI models for authorship identification for written content (Q3 2020)
Development of AI models for fake news identification for written content (Q3 2020)
Development of AI models for fake news identification for written content (Q3 2020)
Develop the STT benchmarking new metrics for 2.0.0 on Github (Q4 2020)
Open-source libraries to facilitate the development and the deployment of microservices-based architectures in serverless clouds (Q4 2020)
Development of a POC for authorship identification (Q4 2020)
Development of a POC integrating fake news and authorship identification (Q4 2020)
2019
EBUCore 1.9 (Q1 2019)
CCDM 2.1 (Q1 2019)
IBC 2019 booth MCMA demonstration (Q3 2019)
AWS and Azure services (speech/text processing, face recognition, and front-end) (Q3 2019)
Update of the MCMA git with cleaned libraries and node.js (Q3 2019)
MDN Workshop 2019 (Q3 2019)