New tool optimises acoustics in virtual reality to help people with hearing difficulties join in
This week at the ISE trade fair in Barcelona, the Eurecat technology centre is showcasing a tool for optimising acoustics in virtual reality and audiovisual production which enhances understanding in virtual environments and helps people with hearing difficulties to take part by tapping deep learning algorithms and binaural audio.
The innovation, boosting acoustics in virtual reality, which has been developed as part of the European GuestXR project, “significantly reduces reverberation, background noise and other disturbances captured by the microphones built into virtual reality glasses which sometimes make it difficult to understand speech and locate resources in space,” says Adan Garriga, director of Eurecat’s Multimedia Technologies Unit.
The innovation also envisages “combining voice analysis tools and multisensory devices for efficient communication in virtual reality by anticipating participants’ varying hearing levels,” says Umut Sayin, head of the Audio Line at Eurecat’s Audiovisual Technologies Unit.
Unlocking interactions and minimising conflicts in the virtual environment
The GuestXR project has shaped an immersive virtual social environment which “integrates a machine learning agent designed to unlock interactions between participants and minimise conflicts,” notes Umut Sayin.
The project harnesses artificial intelligence, neuroscience and social psychology research to foster greater understanding and enhance the experience of participants in shared augmented or virtual reality spaces.
The GuestXR consortium is coordinated by the Eurecat technology centre together with the University of Barcelona and made up of eight organisations from six countries featuring a multidisciplinary team with backgrounds in extended reality, machine learning, artificial intelligence, social psychology, neuroscience, multisensory integration, research ethics and technology transfer.
Alongside Eurecat, four universities (the University of Maastricht, the University of Warsaw, the University of Barcelona and Reichman University), a research institute (Inria) and two businesses (Virtual Bodyworks and g.tec medical engineering GmbH) are also partnering the project.
