AI-powered glasses give wearers ‘superpower' hearing
The glasses – built by a team from Scottish universities Heriot-Watt, Edinburgh, Napier and Stirling – were trained on noise samples including washing machines and traffic.
The researchers hope the new smart glasses can help millions of adults worldwide who have hearing loss severe enough to make conversation difficult.
'We're not trying to reinvent hearing aids. We're trying to give them superpowers,' said Mathini Sellathurai from Heriot-Watt University in Edinburgh.
'You simply point the camera or look at the person you want to hear. Even if two people are talking at once, the AI uses visual cues to extract the voice of the person you're looking at.'
The process requires a lot of computer processing, with the sound data sent to servers in Sweden. Despite the distance, the researchers claim that high-speed broadband or 5G make it 'feel instant'.
The technology is primarily aimed to support people who use hearing aids and have visual impairments, however, it is general enough to be used by anyone working in noisy places like oil rigs or busy venues.
'There are only a few big companies that make hearing aids, and they have limited support in noisy environments,' said Professor Sellathurai. 'We want to break that barrier and help more people, especially children and older adults, access affordable, AI-driven hearing support.'
The researchers are already in talks with hearing aid manufacturers and hope to have a working version of the glasses ready by next year.
They also plan to make the cloud-based model public to allow anyone with a compatible device to benefit from the technology.
Try Our AI Features
Explore what Daily8 AI can do for you:
Comments
No comments yet...
Related Articles
Irish Independent
4 days ago
- Irish Independent
AI-powered glasses give wearers ‘superpower' hearing
Equipped with a camera to translate lip movements into speech, the smart spectacles deliver cleaned up audio for people with hearing difficulties – or anyone in a noisy environment. The glasses – built by a team from Scottish universities Heriot-Watt, Edinburgh, Napier and Stirling – were trained on noise samples including washing machines and traffic. The researchers hope the new smart glasses can help millions of adults worldwide who have hearing loss severe enough to make conversation difficult. 'We're not trying to reinvent hearing aids. We're trying to give them superpowers,' said Mathini Sellathurai from Heriot-Watt University in Edinburgh. 'You simply point the camera or look at the person you want to hear. Even if two people are talking at once, the AI uses visual cues to extract the voice of the person you're looking at.' The process requires a lot of computer processing, with the sound data sent to servers in Sweden. Despite the distance, the researchers claim that high-speed broadband or 5G make it 'feel instant'. The technology is primarily aimed to support people who use hearing aids and have visual impairments, however, it is general enough to be used by anyone working in noisy places like oil rigs or busy venues. 'There are only a few big companies that make hearing aids, and they have limited support in noisy environments,' said Professor Sellathurai. 'We want to break that barrier and help more people, especially children and older adults, access affordable, AI-driven hearing support.' The researchers are already in talks with hearing aid manufacturers and hope to have a working version of the glasses ready by next year. They also plan to make the cloud-based model public to allow anyone with a compatible device to benefit from the technology.
The Journal
5 days ago
- The Journal
AI-powered ‘hearing glasses' will use lip-reading technology to help people with hearing loss
ARTIFICIAL INTELLIGENCE IS being used to create 'hearing glasses' that use lip reading technology to help people with hearing loss. The project by researchers at several universities in the UK aims to help people with hearing loss by filtering out background noise in real-time, even in loud environments. The technology combines lip-reading technology, artificial intelligence and cloud computing and uses a small camera built into glasses to track the speaker's lip movements while a smartphone app uses 5G to send both audio and visual data to a cloud server. AI then isolates the speaker's voice from surrounding noise and sends the cleaned-up sound back to the listener's hearing aid or headphones almost instantly. If two people are talking at once, the AI uses visual cues to extract the voice of the person being looked at. Researchers hope to have a working version of the glasses by 2026. Advertisement Noise samples from a range of sound sources, from washing machines to traffic, have been collected to improve the system's training. Project leader Professor Mathini Sellathurai of Heriot-Watt University in the UK said: 'We're not trying to reinvent hearing aids. We're trying to give them superpowers. You simply point the camera or look at the person you want to hear.' 'Even if two people are talking at once, the AI uses visual cues to extract the voice of the person you're looking at.' Some noise-cancelling technologies already exist but struggle with overlapping voices or complex background sounds, something this system aims to overcome. By shifting the heavy processing work to cloud servers, the researchers can apply' glasses 'could help anyone working in noisy places, from oil rigs to hospital wards'. 'There are only a few big companies that make hearing aids and they have limited support in noisy environments,' he said. 'We want to break that barrier and help more people, especially children and older adults, access affordable, AI-driven hearing support.'
Irish Independent
6 days ago
- Irish Independent
ATU researchers achieve breakthrough in 3D printing technology
The research is led by Dr Aswathy Babu and a multidisciplinary team of researchers supervised by Prof Suresh C. Pillai. The work was carried out in collaboration with the University of Glasgow, Heriot-Watt University, and I-Form, the SFI Research Centre for Advanced Manufacturing at University College Dublin. This cutting-edge innovation overcomes long-standing challenges associated with high-temperature processing and weak interfacial bonding between polymers and fabrics, unlocking new possibilities for next-generation wearable energy harvesting systems. This work was published in the journal Nano Energy in June 2025. This innovation directly addresses several key limitations in the field: it eliminates the need for adhesives or complex multi-step processes, achieves excellent adhesion between the 3D-printed polymer and textile, and delivers robust triboelectric performance. The fabricated devices show high output voltage and current, superior durability, and real-world functionality, including the ability to power small electronic devices and enable IoT-based touch sensing. These properties make the technology ideal for applications in wearable health monitoring and environmental sensing. The team's breakthrough centres on the fabrication of textile-based triboelectric nanogenerators (T-TENGs), capable of converting mechanical motion into usable electrical energy. Using a low-cost fused filament fabrication (FFF) 3D printing technique, the researchers successfully deposited polypropylene (PP)—a triboactive thermoplastic—onto conductive, flexible fabrics. The result is a mechanically robust, finely patterned surface that enables strong dielectric-fabric adhesion and exceptional triboelectric performance. ADVERTISEMENT Professor Suresh C. Pillai, Irish Principal Investigator of the RI-EPSRC project and Head of the Nanotechnology and Bioengineering Research Group at ATU, said; 'This is a significant milestone in wearable energy technology. 'Our direct 3D printing technique creates a highly uniform and intimate bond between the dielectric polymer and the fabric electrode. 'This interface quality is crucial for boosting energy conversion efficiency. 'Through advanced surface patterning and multilayer optimisation, we've significantly enhanced triboelectric output compared to traditional fabrication methods.' Lead researcher, Dr Aswathy Babu added; 'This research provides a scalable and cost-effective route to integrate energy harvesting technologies into everyday clothing. 'By leveraging low-cost 3D printing and achieving strong bonding between polymer and fabric, we have enabled the development of washable, stretchable, and high-performance energy generators suitable for real-world applications.' This research is part of a €1.5 million collaborative project funded by Research Ireland (formerly SFI) and the UK Engineering and Physical Sciences Research Council (EPSRC). The consortium is led by Prof Daniel Mulvihill of the University of Glasgow, and includes researchers from ATU, Tyndall National Institute, and Heriot-Watt University, UK. The project's overarching goal is to harness human motion as a renewable energy source using triboelectric nanogenerator (TENG) technology—an eco-friendly and sustainable energy harvesting approach. The resulting T-TENGs are not only highly efficient but also flexible, durable, washable, and scalable—key attributes for real-world deployment. Demonstrating their practical applicability, the team successfully integrated these energy harvesters into an IoT-enabled adaptive touch sensing system, pointing to immediate potential in domains such as smart wearables, real-time health monitoring, soft robotics, and environmental sensing. 'This work marks a pivotal step toward the development of truly self-powered wearable electronics,' added Prof. Suresh C. Pillai. 'By combining material science, additive manufacturing, and IoT integration, we're laying the groundwork for a new generation of sustainable, user-friendly, and intelligent devices capable of real-time data tracking and wireless connectivity.' Congratulating the research team, ATU President, Dr Orla Flynn said; 'I want to commend Prof Suresh C. Pillai, Dr Aswathy Babu, and the wider research team for their ambition and dedication in addressing real-world challenges through applied science. 'Their work in wearable technology highlights the potential of smart materials to transform how we monitor health, interact with our environment, and power the devices we use every day.' The research sets the stage for commercial-scale production of customisable, self-sustaining electronic textiles for wearable electronics. It opens new horizons in energy-autonomous devices that respond and adapt to their users and environments.
