What’s the Project About?
Speech is a highly variable signal that is often recorded in complex environments and under sub-optimal conditions. The information contained in a recorded speech signal is not limited to just the words spoken; the signal also includes, for example, information on speaker identity or conversation style. Depending on the task at hand, different aspects of the speech signal are important, leading to different models being used. However, in recent years model topologies for automatic speech recognition and many other speech processing tasks have started to converge - driven by research focus on generalisation. Still, the issue of domain dependence often remains. Recently there has been an increased interest in model combination and model editing, for example through disentanglement of so-called task vectors.
In this project we aim to explore how different aspects of speech data are expressed in model space, in the context of automatic speech recognition and diarisation. The objective of this work is to explore methods to attribute elements of model spaces to skills, or specific aspects of the data. This can be used either as input in hypermodelling, where new models for specific domains are generated, or for improved structuring in model training and design.
Work on this project will require research into novel methods to represent model variations and attribute them to specific attributes and tasks. The value of such models should then be demonstrated by informing training and inference processes. A range of different strategies can be explored, including new ways to derive model distributions and model parameter predictions. Experiments should be conducted on a range of tasks of different complexity in the context of different data domains, for example speech classification, speech recognition, and diarisation.
About the School and Research Group
You will be a member of the Speech and Hearing research group in the School of Computer Science at the University of Sheffield and an affiliated member of the UKRI AI Centre for Doctoral Training (CDT) in Speech and Language Technologies (SLT) and their Applications. In the School of Computer Science, 99% of our research was rated in the highest two categories in REF2021 (world-leading or internationally excellent).
What you’ll need
* A high-quality undergraduate (ideally first class) or masters (ideally distinction) degree in a relevant discipline such as Computer Science, Engineering (e.g., electrical and electronic engineering, control engineering, etc.), or Mathematics.
* Strong mathematical aptitude (minimally to UK A-Level standard or equivalent)
* Good experience of programming.
Funding
* Full funding for 3.5 years covering Home or International tuition fees
* Enhanced stipend (standard UKRI rate plus £3,500 totalling £25,305 tax free for 2026/27).
* A research and training support grant of £2,500 pa (pro rata) to cover research expenses and conference attendance.
Interested? Apply Now!
The deadline for applications is 23:59 on 19th April 2026. Shortlisted candidates will be invited to interview either in Sheffield or via videoconference in early- to mid-May. Eligibility and guidance on how to apply can be found here: slt-cdt.sheffield.ac.uk/apply
For an informal discussion about your application please contact us at: sltcdt-enquiries@sheffield.ac.uk
£25,305. Full funding for 3.5 years (Home or International fees). UKRI min stipend plus £3,500 pa enhancement
#J-18808-Ljbffr