Audio and Media Technologies

Which technology trends are shaping the future of large language models (LLMs) – and what makes Europe’s role unique? In this interview, Jan Plogsties, Head of the Generative AI Department at Fraunhofer IIS, explains what the institute is currently researching and where those developments are heading.

Read more

The technology behind these three letters has become an inseparable part of our daily lives: in 2025, the file extension “.mp3” celebrates its 30th anniversary. This audio format laid the foundation for many more groundbreaking audio codecs made in Erlangen. An innovation that began at Fraunhofer IIS and continues to resonate globally.

Read more

Allinga harnesses advanced speech recognition and synthesis to enable natural communication between humans and machines, adapted to the working environment and sector. This allows customized language solutions to be used in industry while conforming to data protection regulations.

Read more

AI language models have fundamentally transformed the way people interact and work with artificial intelligence (AI). Yet for many European companies, existing solutions raise concerns regarding data protection and information security. In collaboration with a broad network of academic and industry partners, Fraunhofer IIS has developed Teuken-7B—an efficiently trained European language model that is available as open source and fully compliant with EU data protection regulations.

Read more

Conference calls that almost feel as if the participants were in the same room? This dream could soon come true thanks to the Immersive Voice and Audio Services (IVAS) codec, a technology that creates a spatial experience during phone calls or teleconferences. IVAS makes conversations feel more vivid, which improves communication. 

Read more

AI algorithms that generate text, images, or videos based solely on prompts – i.e., input in human language – will play a major role in business, research, and society in the future. Known as generative algorithms, these broaden the options for making use of artificial intelligence. And Fraunhofer IIS is at the forefront of their development.

Read more

Clear sound, even when you are surrounded by noisy traffic or your colleague is hammering on their keyboard? A team at Fraunhofer IIS developed a low-complexity real-time AI-based noise reduction technology. What makes it unique is that it is device independent.

Read the article

About 19 years ago, Fraunhofer IIS and the Chair of Information Technology (LIKE) at the Friedrich-Alexander-Universität Erlangen-Nürnberg (FAU) founded a digital campus radio station. It was a research project aimed at testing technical innovations and digital broadcasting systems and working with FAU students on developing innovative, content-related concepts. The campus radio station has long since outgrown its status as a research project, and in 2022, the broadcasting studio moved from Erlangen’s E-Werk cultural center to the “Blue House” on the Europa Canal in Erlangen. On the occasion of this move, we take a look back at 19 years of fruitful collaboration.

Read the interview

In a recent interview Joachim Keinert, head of the “Computational Imaging and Algorithms“ group, shares his insights on light-field, which optimizes editing scenes during the postproduction process.

Read the interview

Gender bias and bias in general play an increasing role in natural language processing. AI applications use vast amounts of data to learn associations relating to all kinds of variables or features. But in doing so, they also adopt existing prejudices and stereotypes. In this interview, Dr. Alessandra Zarcone discusses whether gender bias is also a factor in industrial natural language processing, to what extent she herself is concerned with the issue, and whether Fraunhofer IIS is addressing this problem.

Read the interview

New sound technologies make it possible to craft highly realistic audio experiences in which the sound comes from all sides – even from above. Sound engineer Daniela Rieger completed her Master of Engineering at Stuttgart Media University and is part of the team in the Media Systems and Applications department at Fraunhofer IIS, where she works to optimize these types of audio formats.

Read the article

Transmitting 4K and 8K resolutions in production quality via Ethernet can’t be done? Think again! The new JPEG XS video codec was “custom designed“ for the migration of broadcast studios and productions to Internet Protocol (IP). Building on JPEG XS, we developed a software-based en-/decoding solution that has come through its baptism of fire as a market-ready solution for production under real conditions. Together with the Japanese broadcaster NHK, we have successfully completed a pilot test for 8K transmission.

Read the article

Audio description for video over MPEG-H audio now available in eight languages.

See the video

Speakers tell us about their experience with the webinar series at Fraunhofer IIS.

Read more

Voice assistants are growing in popularity and are even being adopted in industry. To work reliably, they need to »hear« voice commands clearly and must be trained to understand what is being said. A platform »made in Germany« is needed in order to retain ultimate control over these training models and the data the assistant collects. The Fraunhofer SPEAKER project is pursuing precisely that objective.

Read more

Voice assistants such as Alexa, Siri and the like are becoming more and more popular, but the systems struggle when it comes to understanding complex contents and context or deriving semantic meaning. Birgit Brüggemeier knows what the problem is: »The machine lacks common sense.« Together with her project team, she is working on the European version of a voice assistant, looking at how these error messages can be communicated to the user without them getting annoyed and ending their interaction with the voice assistant.

Read more