Since starting her PhD in 2006, Julie has been exploring the overarching research area of designing intelligent systems for processing and modelling temporal data. This primarily involves investigating the architectures and learning algorithms of neural networks for a variety of data sources, including numerical, audio, images, video, 3D, etc.
The work began during her PhD in Computing and Intelligent Systems at Ulster University with the development of architectures and networks of spiking neuron models to simulate the sound localisation capability of the mammalian auditory pathways. During her first post-doctoral research position at Ulster University, the research progressed to adapting these spiking neural architectures to operate in an efficient and low-cost way on a mobile robot. The aim was to provide an ideal platform for the development of a human-like auditory system, which can operate in a dynamic and noisy environment.
In 2011, Julie moved to Queen Mary, University of London and applied these computational intelligence techniques to the domain of virtual 3D data for the development of immersive experiences. She worked as the technical lead for the FP7 collaborative project "Real and Virtual Engagement in Realistic Immersive Environments (REVERIE)", Grant No 287723. This project focused on the implementation and integration of cutting-edge technologies related to 3D data acquisition and processing, sound processing, autonomous avatars, networking, real-time rendering, and physical interaction and engagement in virtual worlds. The aim was for users to meet, socialise and share experiences using equipment they already have at home, along with a range of content creation tools we built for the platform. The possibilities of this type of technology are endless and we developed real-world scenarios, which were trialled by real-world users, such as primary school students attending a virtual field trip to the European Parliament and families communicating virtually using a type of 3D Skype.
In 2015, Julie moved to UEL as a Senior Lecturer and later became Programme Leader for BSc (Hons) Computer Science. Her research now focuses primarily on deep neural networks for speech enhancement and recognition and she maintains collaborative R&D links with the industry. This has led to the successful acceptance of two Innovate UK grants with a combined total value of £2,273,177; UEL's portion amounts to £745,479.