Skip to content

Funded PhD Opportunity

Accessible Tinnitus Notch Noise Therapy via Machine Learning, Acoustic Metamaterials and Additive Manufacturing

  • Project Supervisors: Prof Jon Barker and Dr Anton Krynkin
  • Partners: NHS and TinnitusUK

Funded position for EPSRC CDT Studentship

Application Deadline: 11th January 2026

Project Outline

Over seven million people in the UK live with tinnitus — the persistent perception of sound when no external source is present. Tinnitus can cause distress, anxiety, and loss of concentration, and current therapies are often costly, complex, or inaccessible. This project aims to change that by combining machine learning, clinical expertise, and acoustic sub-wavelength structures (a.k.a. metamaterials) and additive manufacturing to create an affordable, personalised therapy that requires no electronics or batteries. The outcome will be a sustainable, accessible treatment—one that uses sound science to improve lives through innovative, low-cost, and environmentally friendly technology.

Further project information

Notch noise therapy is a promising treatment for tinnitus – the perception of sound in the absence of an external source. Instead of masking tinnitus with more noise, this approach removes a narrow “notch” in the frequency band matching the patient’s tinnitus pitch. Over time, this helps to retrain auditory pathways in the brain, reducing the perceived loudness and distress caused by tinnitus. However, existing implementations rely on electronic devices that are costly and inaccessible for many sufferers.

This PhD project aims to make tinnitus notch noise therapy widely accessible through a combination of machine learning, clinical data modelling, and 3D-printed acoustic metamaterials. The central research question is:

  • How can personalised tinnitus therapy be delivered effectively using passive acoustic devices designed from perceptual and machine learning models?

The project has two main stages:

  1. Tinnitus Profiling and Modelling – Collaborate with tinnitus patients to map perceptual profiles through sound matching and subjective descriptions. Develop machine learning models and explore large language models (LLMs) to infer tinnitus parameters from natural language descriptions and NHS data.
  2. Passive Therapy Design – Use additive manufacturing technology to design and prototype acoustic metamaterial filters tuned to each patient’s tinnitus profile, enabling notch-filtering therapy without electronics.

The project will be co-supervised by experts from Computer Science, Mechanical Engineering, and Sheffield Teaching Hospitals, ensuring a strong link between clinical application and technical innovation.

Sheffield Teaching Hospitals will provide access to clinical expertise and patient cohorts, ensuring that the research is grounded in real clinical need and focused on outcomes that can translate directly into NHS practice. Their involvement will also help guide validation studies and inform regulatory pathways for future deployment.

Key references

  • Mizukoshi, F. et al. (2023). Biomedical Engineering Advances, 6, 100102.
  • Mizukoshi, F. & Takahashi, H. (2021). PLOS ONE, 16(10), e0258842.
  • Tong, Z. et al. (2023) Ear Hear 44(4):670-681

Required qualifications/skills

  • A good undergraduate or master’s degree (2:1 or above, or equivalent) in Computer Science, Engineering, Acoustics, Physics, or a closely related field.
  • Experience in one or more of the following areas:
    • Machine learning, signal processing, or data modelling
    • Audio/acoustic analysis or human perception studies
    • 3D design and additive manufacturing
  • Human-computer interaction or app development (desirable)
  • An interest in applying computational and acoustic research to real-world clinical problems.

How to Apply

Application Deadline: 11th January 2026

The PhD is funded via the EPSRC Centre for Doctoral Training for Sustainable Sound Futures. To apply, please visit the Sound Futures CDT website for application instructions. (Note - the application process is hosted by the University of Salford but the PhD will be based at the University of Sheffield).