Real-Time Magnetic Resonance Imaging for Vocal Tract Analysis

Summary

Supervisor

Associate Professor Craig Jin.

Research location

Electrical and Computer Engineering

Synopsis

Project Description:

The Computing and Audio Research Lab at the University of Sydney, Australia has a fully funded PhD position open to support real-time magnetic resonance imaging (rtMRI) and analysis together with acoustic-phonetic analysis. A particular focus for the imaging/acoustic processing and analysis is to support a study of the developmental trajectory of tongue control. This project is conducted in collaboration with University of York, Macquarie University, and the Discipline of Speech Pathology at the University of Sydney. Applicants with a strong background in Electrical, Computer Engineering, Computer Science, or similar programs are encouraged to apply.

This research seeks to develop rtMRI capabilities for vocal tract analysis in Australia, expand our knowledge of the morphoacoustics (morphoacoustics.org) of the vocal tract and assist with improved understanding and techniques within the field of Speech Pathology.

Challenges arise to validate, correlate, and relate the imaging and acoustic data obtained from vocal tract rtMRI (VT-rtMRI). We will be creating, collecting and analysing an Australian speech database. Research areas of interest are statistical and machine learning techniques to assist with the data analysis and processing. In particular, VT-rtMRI offers the ability to form an improved understanding of the relationship between articulation, acoustics and perception.

The project's aims include:

• Characterising the relationship between dynamic tongue configuration and speech acoustics, and how this relationship changes as the participants grow
• Developing computational imaging and acoustic analysis technologies for establishing these links including novel methods for processing rtMRI images of the vocal tract
• Supporting development of tools to support rtMRI vocal tract imaging and analysis

Research Environment

Embedded in the School of Electrical and Computer Engineering, the Computing and Audio Research Lab is focused on signal processing and machine learning approaches to support morphoacoustic and auditory sensory augmentation research and offers rich collaboration and supervision spanning multiple departments and universities: (Amelia Gully, forensic and acoustics, University of York), (Kirrie Ballard, Speech Pathology, The University of Sydney), (Michael Proctor, speech production, perception, and phonological organisation, Macquarie University), (Luping Zhou, medical imaging and machine learning). We will conduct our research using imaging facilities at Westmead Hospital.

Additional information

Offering:

A fully funded 3.5-year PhD scholarship covering tuition fees and a stipend covering living expenses.

Successful candidates will have:

• A bachelor’s degree in a relevant discipline
• Interest in developing acoustic and imaging analysis systems for VT-rtMRI.
• Excellent communication and interpersonal skills
• Experience with one or more of acoustics, audio signal processing, imaging, image processing and/or computer vision
• Hands-on experience with MATLAB, Python, and Deep Learning frameworks would be a strong asset

Domestic and international applicants are welcome.

How to Apply:

To apply, please email craig.jin@sydney.edu.au the following:

• CV
• Transcripts

Want to find out more?

Opportunity ID

The opportunity ID for this research opportunity is 3530

Other opportunities with Associate Professor Craig Jin