Machine learning models in ultrasound tongue imaging for the detection of children's speech disorders

Currently in Speech and Language Therapy (SLT), technological support is sparse. Assessment of speech disorders is particularly time consuming and suffers from a lack of technological solutions. Normally speech assessment involves listening to the child and writing down what they say. This approach can miss important subtleties in the way children speak. For example, a child may try to say "key" and it may be heard as "tea". This leads the SLT to believe the child cannot tell the difference between t and k and select a therapy designed to tackle this. However, using medical ultrasound to image tongue movements reveals that in many cases children are producing imperceptible errors. This is particularly the case for children with cleft lip and palate who produces a wide variety of unusual speech errors. However, ultrasound analysis is a time consuming task which can only be carried out by a speech scientist with specialist training. This project aims to use machine learning approaches for method for classifying tongue shapes in children with cleft lip and palate. This has the potential to be useful both for assessment and for measuring progress in intervention. Open source data from children with cleft lip and palate is available and an ongoing clinical project with NHS Greater Glasgow and Clyde is currently collecting further ultrasound data.

FUSE has been designed to maximise impact in partnership with industry, international academics, and other organisations such as NPL and the NHS. It includes funded mechanisms to deal with opportunities in equality, diversity and integration (EDI) and in realisation of impactful outcomes.

EDI is aimed at realising the full potential of the talented individuals that join FUSE. Funding mechanisms include support for ten undergraduate internships to prime the pipeline into FUSE research studentships; part-time studentships reserved for people with specific needs to access this route; and talent scholarships for people from Widening Participation backgrounds. Additionally, cultural issues will be addressed through funded support for work life-balance activities and for workshops exploring the enhancement of research creativity and inventiveness through diversity.

People: As a community, FUSE will contribute to impact principally through its excellent training of outstanding people. At least 54 EngD and PhD graduates will emerge with very high value skills from the experience FUSE will provide in ultrasonics and through highly relevant professional skills. This will position them perfectly as future leaders in ultrasonics in the types of organisation represented by the partners.

Knowledge: FUSE will also create significant knowledge which will be captured in many different forms including industrial know-how, patents and processes, designs, and academic papers. Management of this knowledge will be integrated into the students' training, including data management and archival, and will be communicated effectively to those in positions to exploit it.

Economic Gain: In turn, the people and knowledge will lead to the economic impact that FUSE is ultimately designed to generate. The close interaction between the FUSE academics, its research students and industry partners will make it particularly efficient and, since FUSE includes both suppliers and customers, the transition from knowledge creation to exploitation will be accelerated.

Societal Benefit: FUSE is well placed to deliver a number of societal benefits which will reinforce our researcher training and external partner impacts. This activity encompasses new consumer products; improved public safety through advanced inspection across many industrial sectors; and new modalities for medical surgery and therapy. In addition, FUSE will provide engaging demonstrators to promote education in science, technology, engineering and maths, helping replenish the FUSE pipeline and supporting growth of the FUSE community far beyond its immediate members.

Impactful outcomes will gain from several specific funding mechanisms: horizon scanning workshops will focus on specific ultrasonic engineering application areas with industrial and other external participation; all FUSE students will have external partners and both industrial and international academic secondments will be arranged, as well as EngD studentships primarily in industry; and industry case studies will be considered. There will also be STEM promotion activity, funding ultrasonic technology demonstrators to support school outreach and public science and engineering events.