The aim of a Taste of Research project in this area is the preliminary investigation and development of a novel idea that explores the use of Assembly Calculus models in speech processing.
Despite the rapid advances in generative AI, they are no match for biological intelligence. Current AI systems depend on vast amounts of data and often fail to generalise when confronted with unseen or novel tasks, due to the lack of a world model. This project aims to develop a new paradigm for a neurosymbolic AI that moves away from conventional deep learning by unifying model structures, learning paradigms, and world models. Central to the proposed approach is a biologically inspired cognitive architecture based on Assembly Calculus. The overall goal of this research is to develop scalable and efficient AI capable of robust generalisation bring us closer to human-like cognition.
School
Electrical Engineering and Telecommunications
Research Area
Next‑generation AI architectures | Neurosymbolic intelligence | Biologically inspired cognitive modelling
Suitable for recognition of Work Integrated Learning (industrial training)?
No
- Research environment
- Expected outcomes
- Supervisory team
- Reference material/links
The work environment will be within the UNSW Speech Processing Lab in the School of Electrical Engineering and Telecommunications. The group is home to 4 full-time academic staff members, multiple research students, and postdoctoral research fellows, all of whom are actively engaged in research related to speech processing, emotion recognition, disordered speech, and mental state detection.
At the completion of the project, the student will have a good understanding of assembly calculus models, AI, speech signal processing and statistical modelling more broadly. In addition, they will have significantly strengthened their technical/research skill as well as programming skills in MATLAB, Python, or Julia. It is anticipated that by the end of the project, the student will have developed and validated an assembly calculus based model for a chosen speech processing system and implemented this as easy to use code/toolbox in MATLAB, Python, or Julia with documentation. If the topic were extended into an honours thesis, more would be possible.
