idw – Informationsdienst Wissenschaft
Nachrichten, Termine, Experten
Nachrichten, Termine, Experten
“Listening Effort Meter” helps in post-productions to avoid poor speech clarity
Implemented as a plug-in, the “Listening Effort Meter (LE-Meter)” developed by Fraunhofer IDMT in Oldenburg allows sound engineers to visualize listening effort during mixing and conduct post-mixing checks to optimize audio quality. The technology has once again found its way from scientific development into commercial application and is intended to bring about improvements in media production on a broad scale.
Speech intelligibility and listening effort when consuming media are significant issues for many people. The mixing of music and speech in modern productions poses a substantial challenge for many listeners. This problem is further exacerbated by increasing hearing loss. The Fraunhofer IDMT in Oldenburg has developed the LE-Meter for sound engineers to enhance consumer media enjoyment and enable participation for a broader audience.
The ability for a listener to understand a piece of dialog is affected by many factors. This includes, for example, the listeners’ hearing ability, listening environment, placement of speakers and supporting visuals. Because these factors cannot be controlled during production, it is all the more important to monitor other factors which can be controlled before broadcasting, such as enunciation, reverb and effects, loudness of speech or background noise. Fraunhofer IDMT therefore developed the software tool LE-Meter, which allows sound engineers to visualize listening effort during mixing and conduct post-mixing checks to optimize audio quality. Designed to objectively assess the listening effort of dialog in broadcast material, the LE-Meter combines technologies based on automatic speech recognition and psychoacoustic modeling with metrics to evaluate the intelligibility of dialog.
From scientific development into commercial application
“Our Listening Effort Meter enables the objective measurement and display of speech intelligibility and listening effort. Thanks to validations and optimizations using formal listening tests this provides media producers and sound engineers with a precise tool for analyzing and implementing audio content. For example, difficult sections can by identified automatically for improvement with respect to listening enjoyment and accessibility,” emphasizes Prof. Dr. Jan Rennies-Hochmuth, Group Leader for Personal Hearing Systems at the Branch for Hearing, Speech and Audio Technology at Fraunhofer IDMT.
When working on an audio project for a long time, the human ear becomes accustomed to speech portions which may be difficult to recognize when hearing them for the first time, for example dialects of dialog in heavy background sounds. With the LE-Meter, it is possible to visualize objective speech intelligibility and to reduce the impact of habituation effects on the final audio mix. Several years of hearing research have paid-off. Over the past few years Fraunhofer IDMT has done a lot of hearing research in Oldenburg, for example in the related project “SITA – Speech Intelligibility Transformation & Autocorrection”. In 2020 the researchers have brought speech intelligibility measurements into application. Since then, the measurements can be done in real time, controlled by artificial intelligence. The algorithms are based on neural networks and enable an automatic and target group specific measurement of speech intelligibility. They were tested with subjects from different age groups in several evaluations.
Now the further development has been integrated into NUGEN Audio’s plug-in DialogCheck. Following a request from a video streaming provider, the plug-in is suited for use in film, television, radio, podcasting and game audio production, as well as post-production environments.
“For broadcasters and streaming services, dialog intelligibility is absolutely critical – if audiences can’t understand what’s being said, they become frustrated and disengaged. Clear, compelling dialog allows the storytelling and emotion to come through. At NUGEN Audio, we recognized the need for a solution that empowers dialog mixers and post-production engineers to objectively assess speech clarity and make informed creative decisions. Partnering with Fraunhofer IDMT gave us access to cutting-edge technology that enabled the development of our new plug-in, DialogCheck. Collaborating with the Fraunhofer IDMT team has been a pleasure –they brought both technical excellence and a strong commitment to solving real-world challenges.", says Dr. Paul Tapper, CEO, NUGEN Audio.
To reliably identify speech activity in the presence of background noises, Fraunhofer IDMT supplied algorithms for the “Dialog Detection” tool in the audio post-production software Nuendo from Steinberg Media Technologies GmbH. Since Nuendo 11 the successful cooperation between Steinberg and Fraunhofer IDMT gives audio professionals the possibility to easily measure, evaluate and display speech intelligibility.
In the future, the LE-Meter can also be used in other applications. For example, it is conceivable that in broadcasting, camera displays could show speech intelligibility measurements at the same time as sound levels. Or in the film industry, the LE-Meter can be used as quality check so that sound engineers do not have to listen to all mixes but can see immediately whether the speech on a recording is intelligible. The Fraunhofer IDMT is therefore seeking partners to bring the technology into further applications.
Hearing, Speech and Audio Technology HSA at Fraunhofer IDMT in Oldenburg
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 stands for 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 the development of hardware and software systems for audio system technology and signal enhancement, the employees at the Oldenburg site are responsible for transferring 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 in the Collaborative Research Centre »Hearing Acoustics«.
Further information on https://www.idmt.fraunhofer.de/en/hsa.html
Contact for the media:
Christian Colmer
Head of Marketing and Communication
Fraunhofer-Institute for Digital Media Technology IDMT
Oldenburg Branch for Hearing, Speech and Audio Technology HSA
Marie-Curie-Str. 2
26129 Oldenburg
Phone +49 441 80097-312
christian.colmer@idmt.fraunhofer.de
https://www.idmt.fraunhofer.de/en/hsa.html
http:///www.idmt.fraunhofer.de/en/hsa.html
The LE-Meter in NUGEN's plug-in DialogCheck offers audio engineers the ability to visualize and opti ...
NUGEN Audio limited
Prof. Dr. Jan Rennies-Hochmuth and his team have developed the “Listening Effort Meter”, which now h ...
Fraunhofer IDMT/Leona Hofmann
Criteria of this press release:
Business and commerce, Journalists, Scientists and scholars
Economics / business administration, Information technology, Media and communication sciences, Social studies
transregional, national
Cooperation agreements, Research results
English
You can combine search terms with and, or and/or not, e.g. Philo not logy.
You can use brackets to separate combinations from each other, e.g. (Philo not logy) or (Psycho and logy).
Coherent groups of words will be located as complete phrases if you put them into quotation marks, e.g. “Federal Republic of Germany”.
You can also use the advanced search without entering search terms. It will then follow the criteria you have selected (e.g. country or subject area).
If you have not selected any criteria in a given category, the entire category will be searched (e.g. all subject areas or all countries).
