Two PhD students in lab coats smiling and looking at some results

Acoustic speech analysis and machine learning in the diagnosis and monitoring of neurodegenerative disorders

Project details for EMC26-6.


Primary supervisor: Prof Suvankar Pal

Other supervisors: Dr Oliver Watts, SpeakUnique

Location: University of Edinburgh


Project description

There is an urgent need for scalablenon-invasive, low burden, and cost-effective biomarkers for diagnosis and monitoring of neurodegenerative disorders including motor neuron disease (MND) and dementia. Speech is an attractive candidate which can be acquired remotely promoting decentralised clinical and research assessments. 

Our inter-disciplinary team of clinicians, speech scientists, programmers, and experts in artificial intelligence (AI) and machine learning (ML) has pioneered implementation of an App co-produced with our patient advisory group for acquisition of voice data from individuals with MND, dementia, Parkinson’s, and multiple sclerosis. 

We have established a globally leading archive of high-quality voices from deeply clinically annotated longitudinal cohorts. Application of advanced AI/ML approaches has yielded preliminary data demonstrating the utility of voice in detection and monitoring of NDDs. 

The successful applicant will work on novel algorithm development and refinement for differential diagnosis of NDDs, prognostication, evaluating determinants of phenotypic heterogeneity, disease monitoring, and language agnostic models. 
 

References

1.    Tam J, Weaver C, Ihenacho A, Newton N, Virgo B, Barrett S, Neale J, Perry D, Smith A, Chandran S Watts O, Pal S, on behalf of the DASH Consortium. Digital App for Speech and Health Monitoring Study (DASH): protocol for a prospective longitudinal case– control observational study for developing speech datasets in neurodegenerative disorders and dementia. BMJ Open 2025;0:e100222. doi:10.1136/ bmjopen-2025-100222

2.    Bowden, M., Beswick, E., Tam, J. Perry D, Smith A, Newton J, Chandran S, Watts O, Pal S. A systematic review and narrative analysis of digital speech biomarkers in Motor Neuron Disease. npj Digit. Med. 6, 228 (2023). https://doi.org/10.1038/s41746-023-00959-9

3.    Wihlborg L, Goodall J, Wheatley D, Webber JJ, Tam J, Weaver C, Pal S, Chandran S, Seth S, Watts O, Valentini-Botinhao C. Evaluating pretrained speech embedding systems for dysarthria detection across heterogenous datasets. arXiv preprint arXiv:2509.19946. 2025 Sep 24.

4.    Webber JJ, Watts O, Wihlborg L, Wheatley D, Tam J, Weaver C, Pal S, Chandran S, Valentini-Botinhao C. Comparator Loss: An Ordinal Contrastive Loss to Derive a Severity Score for Speech-based Health Monitoring. arXiv preprint arXiv:2509.17661. 2025 Sep 22.


Suitable first degree subjects

Speech science, data science, computer science, operational research


Essential/desirable skills and experience

Deep learning, data visualisation, coding, statistics, deep learning, coding, cloud computing, programming


Related links

Project listing on FindaPhD.com
 

Related content

×