HDR-Colour Volume – Colour difference metrics in 3D
With the move from SDR to HDR colours and the corresponding higher luminance range of HDR there seems to be a need to visualise and evaluate certain measurements in 3D as well.
weConnect is live!
by Uwe Felderhoff and Aylin Vogl In the night of 01.12.2020, under the direction of IRT, the ARD radio contribution exchange was switched to weConnect. This was followed on December 9, under the direction of ARD Sternpunkt, by the shutdown of the previous, centralized line dispatching and thus the introduction of the decentralized weConnect line …
German news-articles database for Natural Language Processing
In recent years, the volume of news published and read online has been increasing, making news data an interesting resource for many fields of study, such as investigative journalism, social sciences and linguistics. News articles present a compelling source of data for researchers in numerous domains. With the growth of published news articles online, the manual processing of content uploaded …
Dialog+ – End user tests
The improvement of speech intelligibility for broadcasting content has been an important aspect of IRT’s work for many years. Dialog+ is the name of an additional service with enhanced speech intelligibility that promises to at least improve the current situation. To ensure that these developments are not only valid in a lab context, but also …
A system for Deepfake Detection: DFirt
Synthetic media manipulated by deep learning algorithms have become a matter of public concern due to the fact that they are increasingly realistic and believable and can be used to intentionally mislead public. The term DeepFake refers to synthetic images and videos manipulated by deep learning algorithms that achieve realistic results by swapping a person’s …
Tool for codec-independent NGA productions released
We are very proud to inform you about the first public release of the “EAR Production Suite”, a free set of tools for producing immersive and personalizable audio content independently from the distribution codec. This open-source project has been developed in (yet) another great collaboration with our colleagues from the BBC R&D audio team under …
UHD – what it is about!
Ultra-High Definition – better known as UHD – has been a common term for several years. With it, television viewers benefit from a higher picture quality. But what exactly is behind UHD? We have examined UHD in more detail and with the help of an extensive subjective test we found out which visual factors have …
Responsive graphics – Fullscreen for everyone!
After the switch of the TV format from 4:3 to 16:9, other aspect ratios remained at best a niche product for a long time in the broadcasting industry. But social media are defining entirely new standards on their platforms. This challenges video producers to provide their content to various distribution channels – including the need …
Next Generation Audio for Headphones – the Binaural NGA Renderer
In the course of the AES “Virtual Vienna” Convention 2020, the Binaural NGA Renderer, our binaural rendering addon for the EBU ADM Renderer, was released together with a corresponding paper. The Binaural NGA Renderer was released as an open source project and can be found at https://github.com/IRT-Open-Source/binaural_nga_renderer. The corresponding paper with the title “Optimized binaural rendering …
Deep Learning in multimedia
The advances in Artificial Intelligence (AI) and more specifically in Deep Learning, have hardly left any technical domain unaffected. The idea of Artificial Intelligence is not new, what happened that suddenly Artificial Intelligence has gained so much attention? What is the impact on the multimedia landscape and what are the emerging challenges for broadcasters? Shortly …