The Phonetics group at Lancaster University, UK is looking to appoint a Senior Research Associate (i.e. postdoc) in Machine Learning for Speech Processing. The position is available from 1 July 2026 for 18 months.
The goal is to recover vocal tract movements from the acoustic signal. We are developing ways to integrate physical knowledge into the models, so the inversions are not just accurate but also reveal underlying principles of speech production.
We're looking for someone with strong ML/speech processing skills who is excited about working at the interface of machine learning, physical modelling, and scientific discovery. The project is funded by The Royal Society and is a collaboration between Sam Kirkham (Lancaster), Anton Ragni (Sheffield) and Aneta Stefanovska (Lancaster).
More information
