Beyond standard hearing care

Solutions

For people with hearing difficulties

Receive a precise diagnosis of your hearing problem and an individualized technical solution to maintain your desired quality of life.

For hearing care professionals

Detect hearing loss earlier than what is possible today and benefit from an easier and faster fitting process.

For manufacturers of hearing technologies

Stay ahead with an embedded solution that provides individualized, neural-network-based sound processing for hearables, hearing aids, cochlear implants and automatic speech recognition systems.

Picture by Brent Kirkwood

CochSyn Test

Our diagnostic solution for hidden hearing loss – a patented portable EEG-based measurement system

CoNNear Embedded Algorithm

Our treatment solution for hidden hearing loss – tailored to the personal hearing profile of the CochSyn test

  • With the CochSyn test, we strive to diagnose (hidden) hearing loss before it can be measured by the tools and tests currently available to clinicians.
  • Hidden hearing loss (cochlear synaptopathy) is considered to be one of the earliest signs of hearing loss because it can occur before there is any noticeable decline in a person’s hearing thresholds measured in a standard hearing test.
  • Unlike other types of hearing loss, which are often caused by damage to the hair cells themselves, cochlear synaptopathy affects the connection between the hair cells and the hearing nerve. This means that the hair cells may still be intact, but the signals that they send to the brain are not as clear as they should be.
  • In many cases, a person with cochlear synaptopathy may be able to hear sounds just fine in a quiet environment, but have difficulty hearing or understanding speech in noisy or crowded situations.
  • With the CoNNear algorithm, we aim to improve speech understanding in noise for people with hidden hearing loss.
  • The CoNNear algorithm is a convolutional neural-network model of human cochlear mechanics and filter tuning for real-time applications. The model accurately simulates human cochlear frequency selectivity and its dependence on sound intensity, which is essential for speech understanding in noisy situations.

Selected publications of our technology:

  • Verhulst, Sarah, et al. “Supra-Threshold Envelope-Following Responses in the Ageing Population : An Early Marker of Sensorineural Hearing Damage.” JOURNAL OF THE ACOUSTICAL SOCIETY OF AMERICA, vol. 153, no. 3, Supplement, 2023, pp. A50–A50, doi:10.1121/10.0018124. https://biblio.ugent.be/publication/01HQNEBKSGRPKX79C2NQJ0DWXP
    • Drakopoulos, Fotios, and Sarah Verhulst. “A Neural-Network Framework for the Design of Individualised Hearing-Loss Compensation.” IEEE-ACM TRANSACTIONS ON AUDIO SPEECH AND LANGUAGE PROCESSING, vol. 31, 2023, pp. 2395–409, doi:10.1109/TASLP.2023.3282093. https://biblio.ugent.be/publication/01HGARZMJCNWTQAYFT0QAQ1PYX
    • Drakopoulos, Fotios, et al. “A DNN-Based Hearing-Aid Strategy for Real-Time Processing : One Size Fits All.” ICASSP 2023 – 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), IEEE, 2023, doi:10.1109/icassp49357.2023.10094887. https://biblio.ugent.be/publication/01HZHD15W7HXCZ8B6D46VXQ4CC