Skip to main navigationSkip to main content
The University of Southampton
We're launching a new website soon and would love your feedback. See the new design

Research project: Personalized fitting and evaluation of hearing aids with EEG responses

Currently Active: 

Current clinical practice in hearing aid fitting and evaluation is mostly based on pure tone detection. Besides this, audiologists are dependent on subjective responses from hearing impaired, who are not always willing or capable of giving a response. This multi-centre project aims to optimise hearing aid fitting procedures by providing tools to objectively measure brain activity to natural speech stimuli. This could potentially lead to a better understanding of speech processing in the brain, new approaches in determining patient-specific hearing loss, and new algorithms for patient-specific optimisation of hearing aid devices.

In the UK, it is estimated that about 6 million people would benefit from hearing aids, yet there are only 2 million hearing aid users. Many users will not use their hearing aid regularly, largely due to poor performance and usability of the device. Many users complain of not having any benefit from the device when listening to speech, especially in noisy environments (e.g. restaurants). One of the main reasons is that hearing aids are currently set up using an audiogram, in which potential hearing aid users are asked to respond when they hear a tone. It is however generally recognised that elevated pure-tone hearing thresholds cannot fully explain poor results in speech-in-noise tests. Audiogram tests also require subjective responses of the subject. Some hearing impaired subjects (especially infants and elderly) are not capable to cooperate with subjective testing, which would lead to suboptimal hearing aid fitting.


The current project attempts to tackle these issues by directly measuring brain responses to natural speech using electro-encephalography (EEG). EEG analysis would avoid the need for subjective, voluntary responses from the patient, and has been shown to be useful in detecting responses to short segments of speech stimuli as well as continuous speech. The key research aim is to achieve a robust assessment of hearing function and speech processing in the brain by computer analysis of EEG responses to complex real-world signals. This presents major scientific and technical challenges, needing the development of novel signal-analysis methods for speech and EEG data, which can provide new insights related to hearing impairment and cognition, as well as guiding in hearing aid settings and personalised performance evaluation.

Partner Institutes

University of Manchester

Imperial College London

Interacoustics Research Unit, Technical University of Denmark (DTU)

For more info: see the Staff subpage

This interdisciplinary work will be carried out as a collaboration between universities departments (hearing science, speech processing, signal analysis), industry (hearing technologies) and patients (choosing hearing challenges). The benefits of undertaking this work are expected to be to patients and their family and carers (improved quality of life from using hearing aids), the health-services (improved efficiency), industry (new diagnostic technologies) and the scientific community (better understanding of hearing; improved methods for analysing EEG signals). This project is funded by the Engineering and Physical Sciences Research Council (EPSRC, EP/M026728/1):


Recent publications

Meltzer, B. et al. (2015). The steady-state response of the cerebral cortex to the beat of music reflects both the comprehension of music and attention. Frontiers in human neuroscience 9;436.

Vanheusden, F.J. et al. (2016). Analysis of envelope-following responses to natural vowels using a Fourier Analyzer. Workshop on Auditory Neuroscience, Cognition and Modelling, QMUL, London.

Reichenbach, C.S. et al. (2016). The Auditory-Brainstem Response to Continuous, Non-repetitive Speech Is Modulated by the Speech Envelope and Reflects Speech Processing. Frontiers in computational neuroscience 10

Vanheusden, F.J. et al. (2017). Multichannel frequency-domain Hotelling’s T2 test for detection of envelope following responses to natural vowels. IERASG, Krakow, Poland

Vanheusden, F.J. et al. (2017). Exploration of inter-individual variability in cortical responses to natural English sentences. IERASG, Krakow, Poland.

Vanheusden, F.J. et al (2017). Simultaneous detection of envelope frequency following responses and cortical responses to words using the Hotelling’s T2 Test, BSA, Harrogate, UK

Forte, A.E., et al (2017). The human auditory brainstem response to running speech reveals a subcortical mechanism for selective attention. eLife, in press.



The project team regularly visits public events to demonstrate state-of-the art knowledge on hearing impairment and hearing aid devices. By interacting with the public, we hope to increase awareness on hearing impairment and discuss future developments in hearing aid devices.

University of Southampton Science and Engineering day 2016

Cheltenham Science Festival 2016

Winchester Science Festival 2016

University of Southampton Science and Engineering day 2017

Bestival 2017

Workshop on Speech Evoked Response Measurement, International Evoked Response Audiometry Study Group Meeting, Warsaw 2017

Associated research themes

Bioengineering and Human Factors:

Related research groups

Signal Processing, Audio and Hearing Group

Key Publications

Share this research project Share this on Facebook Share this on Twitter Share this on Weibo
Privacy Settings