Fraunhofer launches optimal speech intelligibility & personal sound technologies at NAMM 2026
Speech Intelligibility Meter, "YourSound" Digital Assistant Sound Optimization, & "Minikraken" Headphone Amplifier AES67 to DSP Technology to be Demoed at NAMM.
Fraunhofer IDMT www.idmt.fraunhofer.de/hsa, a division of one of the world’s leading organizations for applied research, will launch optimal speech intelligibility and personal sound technologies next week at NAMM 2026.
Fraunhofer IDMT’s Oldenburg Branch Hearing, Speech and Audio Technology (HSA) has developed new technologies for optimal audio listening on devices, including the "Your Sound" digital assistant for personalized sound, Listening Effort Meter (LE-Meter) speech intelligibility measurement technology for the objective assessment of speech intelligibility, and "Minikraken" headphone amplifier technology AES67 on DSP hardware (Audio over IP). Available now for licensing, Fraunhofer technologies such as YourSound are being integrated into car and headphone manufacturers’ products and into a variety of other applications.
Supports Post-Production Professionals with Objective Real-Time Analysis of Listening Efforts
Unclear dialogue in a television series, excessively loud background music in reality TV, and sports interviews overlaid with audience cheers can impair the TV viewing experience. In film, television, streaming, or live productions, ensuring good speech intelligibility is one of the biggest challenges for professional sound engineers. Radio, television, and streaming production professionals require a tool to ensure that dialogue is evaluated objectively and is consistently understandable to the audience.
Follow us on: 
Fraunhofer IDMT addresses this need with algorithms that provide recommendations for action based on the objective analysis of listening efforts in real-time. Fraunhofer IDMT has teamed up with partners to bring the most useful solution for post-production professionals. Fraunhofer’s speech intelligibility measurement has been integrated into media technologies for post-production. The measurement is based on AI algorithms and has undergone extensive evaluation and testing. Beyond simple speech intelligibility measurements, additional functionalities are possible, such as automatically marking critical sections in the timeline and automatically improving speech intelligibility.
Fraunhofer "YourSound" Virtual Assistant Lets Listeners Adjust Sound Preference
Fraunhofer IDMT’s new Your Sound digital assistant enables users of audio devices and infotainment systems to adjust audio without technical knowledge. Already implemented by car and headphone manufacturers, Fraunhofer IDMT’s YourSound technology brings personal sound to customers. Researchers from Fraunhofer IDMT have developed a simple and elegant way to personalize sound and audio dynamics in a wide variety of applications.
The audio software allows users to adjust individual sound settings without complex sub-menus or parameters, allowing devices, including Bluetooth speakers, TVs, smartphones, and more, to be adjusted to a user’s personal needs and preferences without technical knowledge.
The technology relies on the presentation of music signals, which users can easily adjust to their preferences through a simple user interface. Once set, the presets enhance overall sound quality, delivering a better listening experience across any sound volume or environment, with music and film audio optimized to individual hearing preferences.
Audio over IP: Fraunhofer IDMT brings AES67 to DSP hardware The Fraunhofer
IDMT Minikraken headphone amplifier lets you route, distribute, and record multi-channel audio using regular network switches instead of traditional audio cabling. Based on cost-efficient DSP hardware, Fraunhofer IDMT-HSA developed a fully functional software stack compliant with the AES67 standard for various audio applications.
AES67 is an open interoperability standard from the Audio Engineering Society (AES) for professional audio over IP (AoIP) that connects various proprietary audio network systems, such as Dante, RAVENNA, and Livewire. The DSP is capable of processing at least 16 channels in/out. Additional signal processing on the DSP can be added depending on the configuration and network architecture, with a latency range from 0.75 to 5 ms. A minimalist web application and discovery implementation allow users to find and connect to other devices on the network or adjust configurations.
Hearing, Speech & Audio Technology (HSA) at Fraunhofer IDMT
Founded in 2008 by Prof. Dr. Dr. Birger Kollmeier and Dr. Jens-E. Appell, the Fraunhofer Institute for Digital Media Technology IDMT’s Branch for Hearing, Speech and Audio Technology (HSA) provides market-oriented research and development with a focus on the following areas:
- Speech and event recognition.
- Sound quality and speech intelligibility.
- Mobile neurotechnology and systems for networked healthcare.
With in-house expertise in hardware and software systems development for audio system technology and signal enhancement, Fraunhofer IDMT transfers scientific findings into practical, customer-oriented solutions. Through scientific cooperation, the institute is closely linked to the Carl von Ossietzky University, Jade University of Applied Sciences, and the University of Applied Sciences Emden/Leer. Fraunhofer IDMT is a partner in the "Hearing4all" cluster of excellence and the Collaborative Research Centre "Hearing Acoustics."