Developmental trajectory of tongue control for speech with real-time MRI. This project aims to evaluate the developmental trajectory of tongue control during speech, relating dynamic 3D vocal tract modelling to the acoustic signal. By optimising real-time MRI technology to capture and model articulatory movements, the project expects to accelerate understanding of how tongue control for speech is developed, mastered, and perturbed by factors such as rapid growth and foreign accent. Expected outc ....Developmental trajectory of tongue control for speech with real-time MRI. This project aims to evaluate the developmental trajectory of tongue control during speech, relating dynamic 3D vocal tract modelling to the acoustic signal. By optimising real-time MRI technology to capture and model articulatory movements, the project expects to accelerate understanding of how tongue control for speech is developed, mastered, and perturbed by factors such as rapid growth and foreign accent. Expected outcome is a new understanding of how different speakers' vocal tracts change and how speech is reshaped, informed by real physiological data. Significant benefits will be realised through refined methods and theory development for diverse fields e.g. linguistics, speech science, and automatic speech recognition/synthesis. Read moreRead less
Damage Detection and Quantification using Infrastructure Digital Twins. Structural health monitoring is vital for infrastructure assets management as early detection of structural conditions is key to both safety and ongoing maintenance. This project combines computer vision, vibration tests, finite element modelling and deep learning technologies to develop an efficient structural health monitoring system. Digital twins created from images taken by cameras or UAVs will be correlated through dee ....Damage Detection and Quantification using Infrastructure Digital Twins. Structural health monitoring is vital for infrastructure assets management as early detection of structural conditions is key to both safety and ongoing maintenance. This project combines computer vision, vibration tests, finite element modelling and deep learning technologies to develop an efficient structural health monitoring system. Digital twins created from images taken by cameras or UAVs will be correlated through deep learning with structural conditions and load-carrying capacities obtained from vibration tests and finite element model analysis for efficient structural damage detection and quantification. The project will lead to effective structural health monitoring and enhance structural safety and reduce maintenance costs. Read moreRead less
Speech recognition adaptation for low resource populations. Automatic speech recognition is an essential attribute of mobile devices and consumer electronics. Unfortunately, as these systems are trained with adult speech, they perform poorly when used by children and people with speaking difficulties. The lack of available training speech from these groups makes developing models for them difficult. We will investigate efficient model adaptation methods that use minimal training data to adapt ex ....Speech recognition adaptation for low resource populations. Automatic speech recognition is an essential attribute of mobile devices and consumer electronics. Unfortunately, as these systems are trained with adult speech, they perform poorly when used by children and people with speaking difficulties. The lack of available training speech from these groups makes developing models for them difficult. We will investigate efficient model adaptation methods that use minimal training data to adapt existing adult speech recognition models for use with children and people with speaking difficulties. The intended outcomes will improve access to automatic speech recognition systems for Australians whose communication with speech-controlled environmental and educational devices is currently restricted.Read moreRead less
Subband centroids and deep neural networks for robust speech recognition. This project aims to improve the robustness and accuracy of automatic speech and speaker recognition systems. Though these systems work reasonably well in noise-free environments, their performance deteriorates drastically even in the presence of a small amount of noise. To overcome this problem, this project proposes a missing-feature approach for robust speech and speaker recognition. This approach is expected to make th ....Subband centroids and deep neural networks for robust speech recognition. This project aims to improve the robustness and accuracy of automatic speech and speaker recognition systems. Though these systems work reasonably well in noise-free environments, their performance deteriorates drastically even in the presence of a small amount of noise. To overcome this problem, this project proposes a missing-feature approach for robust speech and speaker recognition. This approach is expected to make the speech and speaker recognition systems less sensitive to additive background noise and make them more useful in telecommunications and business.Read moreRead less
Ultra-low fouling active surfaces. This project aims to develop chemistries and fabrication approaches through innovative materials evaluation to develop ultra-low fouling active electrode surfaces. Development of ultra-low fouling surfaces will have significant impact in a range of applications where system or device failure is attributed to fouling. The growing field of bionics, where implantable electronic devices interface directly with the nervous system, is one such device. The expected ou ....Ultra-low fouling active surfaces. This project aims to develop chemistries and fabrication approaches through innovative materials evaluation to develop ultra-low fouling active electrode surfaces. Development of ultra-low fouling surfaces will have significant impact in a range of applications where system or device failure is attributed to fouling. The growing field of bionics, where implantable electronic devices interface directly with the nervous system, is one such device. The expected outcomes will be an understanding of the material requirements that lead to the elimination of protein and cell accumulation at surfaces that degrades the performance and lifetime of these implants. The findings will benefit any application where fouling is a problem.Read moreRead less
Adapting Deep Learning for Real-world Medical Image Datasets. The project aims to investigate new deep learning modelling approaches to leverage real-world large-scale image data sets that contain noisy and incomplete labels and imbalanced class prevalence – to enable the use of these data sets for modelling deep learning classifiers. Expected outcomes include an innovative method for modelling deep learning classifiers. The research will involve new inter-disciplinary and international collabor ....Adapting Deep Learning for Real-world Medical Image Datasets. The project aims to investigate new deep learning modelling approaches to leverage real-world large-scale image data sets that contain noisy and incomplete labels and imbalanced class prevalence – to enable the use of these data sets for modelling deep learning classifiers. Expected outcomes include an innovative method for modelling deep learning classifiers. The research will involve new inter-disciplinary and international collaborations with machine learning and medical image analysis research institutions. This should provide significant benefits, such as better understanding of deep learning theory, new deep learning applications that can use previously unexplored data sets, and training for the future Australian workforce.Read moreRead less
Biological determinants of the safety and stability of neuroprosthetic stimulation electrodes. Performance of cochlear implants and the quality of sound perceived by patients is strongly related to electrode impedance. Electrode impedance fluctuates relative to the implant electrical activity, but the mechanisms which cause this are not clear. This project aims to investigate the role of protein adsorption in electrode performance, including impedance and material dissolution. To enable these in ....Biological determinants of the safety and stability of neuroprosthetic stimulation electrodes. Performance of cochlear implants and the quality of sound perceived by patients is strongly related to electrode impedance. Electrode impedance fluctuates relative to the implant electrical activity, but the mechanisms which cause this are not clear. This project aims to investigate the role of protein adsorption in electrode performance, including impedance and material dissolution. To enable these investigations a new biomimetic analogue of the perilymph (cochlea fluid) is intended to be developed. Additionally, the project aims to investigate two strategies to minimise impedance changes: small pulse electrode cleaning and antifouling coatings. Understanding and control of factors influencing electrode stability aim to facilitate next-generation implant designs.Read moreRead less
Automated analysis of multi-modal medical data using deep belief networks. This project will develop an improved breast cancer computer-aided diagnosis (CAD) system that incorporates mammography, ultrasound and magnetic resonance imaging. This system will be based on recently developed deep learning techniques, which have the capacity to process multi-modal data in a unified and optimal manner. The advantage of this technique is that it is able to automatically learn both the relevant features t ....Automated analysis of multi-modal medical data using deep belief networks. This project will develop an improved breast cancer computer-aided diagnosis (CAD) system that incorporates mammography, ultrasound and magnetic resonance imaging. This system will be based on recently developed deep learning techniques, which have the capacity to process multi-modal data in a unified and optimal manner. The advantage of this technique is that it is able to automatically learn both the relevant features to analyse in each modality and the hidden relationships between them. The use of deep belief networks has produced promising results in several fields, such as speech recognition, and so this project believes that our approach has the potential to improve both the sensitivity and specificity of breast cancer detection.Read moreRead less
Targeting electrical stimulation of neural tissue. This project aims to develop a platform of mathematical methods for targeting electrical stimulation of neural tissue. The proposed methods work by selecting the amplitude and polarity of each stimulating electrode in an array based on a desired pattern of neural activation. The algorithms are particularly applicable to high-density electrode arrays. The project will work with an Australian industry leader to provide significant benefits to Aust ....Targeting electrical stimulation of neural tissue. This project aims to develop a platform of mathematical methods for targeting electrical stimulation of neural tissue. The proposed methods work by selecting the amplitude and polarity of each stimulating electrode in an array based on a desired pattern of neural activation. The algorithms are particularly applicable to high-density electrode arrays. The project will work with an Australian industry leader to provide significant benefits to Australia’s high-tech sector through increased knowledge and capacity.Read moreRead less
Feedthrough technologies for polymeric encapsulated active implants. The project will address the scientific challenges of signal transfer between tissue and novel active implantable medical devices, with major implications for cochlear implant manufacture. This will lead to improvements in the quality of life of the hearing-impaired, and will make an important contribution to the development of other sensory implants.