Voice Filtering

In audio mixes, different speakers at the same time are not uncommon – but sometimes this impairs speech intelligibility. Fraunhofer IDMT in Oldenburg has a solution: A technology known as voice filtering, which generates the acoustic fingerprint of a speaker within a few seconds in order to extract it later from a mix of several speakers, enables the reliable recognition and separation of different speakers.

Especially people with hearing impairments can have difficulty concentrating on one person in a group and listening to them. Here, the intelligent algorithms of the voice filtering technology can help to filter out one person from the complex mix and in this way enhance speech intelligibility.

The areas of application for this technology extend beyond media production – it is also used in speech recognition. For example, it can be used so that only a specific person can give voice commands to a system, and ambient noise and other speakers are filtered out.

Christian Rollwage presents the voice filter technology

Privacy warning

With the click on the play button an external video from www.youtube.com is loaded and started. Your data is possible transferred and stored to third party. Do not start the video if you disagree. Find more about the youtube privacy statement under the following link: https://policies.google.com/privacy

Further Information

 

Press information / 4.11.2021

Better understanding

Tonmeistertagung 2021: Fraunhofer IDMT presents solutions for analyzing, evaluating and improving speech intelligibility

 

Your sound, in every situation

Our software solutions are able to measure, display and optimize speech intelligibility – automatically if needed.

 

Analysis and optimization of speech intelligibility

Our software solutions are able to measure, display and optimize speech intelligibility – automatically if needed.

 

Defense against drones

An interview with Christian Rollwage about »drone detection and localisation«. He talks about audio signal enhancement for emergencies.

 

Audio Signal Enhancement

Make use of our specialist expertise and let us develop software and hardware for you to improve your acoustic signals – for audio signals with real added value.

 

Oldenburg Branch for Hearing, Speech and Audio Technology HSA

The objective of the Oldenburg Branch for Hearing, Speech and Audio Technology HSA of the Fraunhofer Institute for Digital Media Technology IDMT is to transfer scientific findings related to hearing perception and man-machine interaction into technological applications.