The new voice of Multicultural Australian English. This project aims to generate an integrated and inclusive model of Australian-English, through phonetic analysis of the spoken language used by adolescents from a range of ethnic backgrounds. Australia is one of the most ethnically diverse countries in the world yet the complex relationship between speech production and cultural diversity is largely unknown in 21st century multicultural Australia. This project aims to establish how adolescents f ....The new voice of Multicultural Australian English. This project aims to generate an integrated and inclusive model of Australian-English, through phonetic analysis of the spoken language used by adolescents from a range of ethnic backgrounds. Australia is one of the most ethnically diverse countries in the world yet the complex relationship between speech production and cultural diversity is largely unknown in 21st century multicultural Australia. This project aims to establish how adolescents from different ethnicities use speech patterns to symbolically express their diverse sociocultural identities. The project expects to inform sociophonetic theories of variation, ethnicity, and identity, providing a framework for supporting sociocultural cohesion in Australia. Read moreRead less
The effect of sound change on children's speech in community diversity. This project aims to explain how children's speech processing adapts to cultural and linguistic diversity and how such adaptation may seed sound change in language. Using acoustic and articulatory (ultrasound) methods, the project intends to explain how children rapidly and authentically acquire the intricately nuanced accents of their communities. The project aims to advance theories of language variation and change by prov ....The effect of sound change on children's speech in community diversity. This project aims to explain how children's speech processing adapts to cultural and linguistic diversity and how such adaptation may seed sound change in language. Using acoustic and articulatory (ultrasound) methods, the project intends to explain how children rapidly and authentically acquire the intricately nuanced accents of their communities. The project aims to advance theories of language variation and change by providing new insights into the forces that shape the sounds of language. An understanding of how children's speech patterns develop and ultimately converge to local norms has implications for the social integration of second language learning children and refugee/asylum seekers, and for clinical and speech technology applications for children.Read moreRead less
A more sound approach to the neurobiology of language. How does the brain attain spoken language? Current neurobiological models assume either implicitly or explicitly that there is no relationship between a word's sound and its meaning. Yet considerable evidence shows this strong assumption about the arbitrariness of language is invalid. This project will use a combination of behavioural, neuroimaging and computational studies to characterise how the brain processes statistical regularities in ....A more sound approach to the neurobiology of language. How does the brain attain spoken language? Current neurobiological models assume either implicitly or explicitly that there is no relationship between a word's sound and its meaning. Yet considerable evidence shows this strong assumption about the arbitrariness of language is invalid. This project will use a combination of behavioural, neuroimaging and computational studies to characterise how the brain processes statistical regularities in sound-to-meaning correspondences as probabilistic cues to attain spoken language. The outcome will be a better neural account of language comprehension and production. The benefit of this new account will be a stronger basis for assessment and treatment of developmental and acquired language impairments.Read moreRead less
Deep visual understanding: learning to see in an unruly world. Deep Learning has achieved incredible success at an astonishing variety of Computer Vision tasks recently. This project aims to convey this success into the challenging domain of high-level image-based reasoning. It will extend deep learning to achieve flexible semantic reasoning about the content of images based on information gleaned from the huge volumes of data available on the Internet. The project expects to overcome one of the ....Deep visual understanding: learning to see in an unruly world. Deep Learning has achieved incredible success at an astonishing variety of Computer Vision tasks recently. This project aims to convey this success into the challenging domain of high-level image-based reasoning. It will extend deep learning to achieve flexible semantic reasoning about the content of images based on information gleaned from the huge volumes of data available on the Internet. The project expects to overcome one of the primary limitations of deep learning and will greatly increase its practical application to a range of industrial, cultural or health settings.Read moreRead less
Discovery Early Career Researcher Award - Grant ID: DE190100539
Funder
Australian Research Council
Funding Amount
$408,000.00
Summary
Towards conversational vision-based Artificial Intelligence. This project aims to develop a novel learning framework, Vision-Ask-Answer-Act (V3A). This framework will allow a machine to perform a sequence of actions via a conversation with human users, based on intricate processing of not just visual input, but human-computer verbal exchanges. Artificial intelligence has great potential as a tool for economic productivity and daily tasks. Applications in cars and assistant robots, still in their ....Towards conversational vision-based Artificial Intelligence. This project aims to develop a novel learning framework, Vision-Ask-Answer-Act (V3A). This framework will allow a machine to perform a sequence of actions via a conversation with human users, based on intricate processing of not just visual input, but human-computer verbal exchanges. Artificial intelligence has great potential as a tool for economic productivity and daily tasks. Applications in cars and assistant robots, still in their early days, typically require significant expertise to use effectively. The outcomes of this project will push the boundary of vision-language research to produce a conversational intelligent agent that can be easily used in common situations across industry, transport, the medical sector, and at home.Read moreRead less
Making Meta-learning Generalised . This project aims to develop novel machine learning techniques, termed generalised meta-learning, to make machines better utilise past experience to solve new tasks with few data. It expects to reduce the undesirable dependence of current machine learning on labelled data and significantly expand its application scope. Expected outcomes of the project consist of new theoretical results on meta-learning and a set of innovative algorithms that can support the bui ....Making Meta-learning Generalised . This project aims to develop novel machine learning techniques, termed generalised meta-learning, to make machines better utilise past experience to solve new tasks with few data. It expects to reduce the undesirable dependence of current machine learning on labelled data and significantly expand its application scope. Expected outcomes of the project consist of new theoretical results on meta-learning and a set of innovative algorithms that can support the building of next generation of computer vision systems to work in open and dynamic environments. This should be able to produce solid benefits to the science, society, and economy of Australian via the application of these advanced intelligent systems.Read moreRead less
Discovery Early Career Researcher Award - Grant ID: DE220100265
Funder
Australian Research Council
Funding Amount
$417,000.00
Summary
A closed-loop human–agent learning framework to enhance decision making. This project aims to design a foundational human–agent learning framework to augment the decision making process, using reinforcement and closed-loop mechanisms to enable symbiosis between a human and an artificial-intelligence agent. It envisages significant new technologies to promote controllability and efficient and safe exploration of an environment for decision actions – drastically boosting learning effectiveness and ....A closed-loop human–agent learning framework to enhance decision making. This project aims to design a foundational human–agent learning framework to augment the decision making process, using reinforcement and closed-loop mechanisms to enable symbiosis between a human and an artificial-intelligence agent. It envisages significant new technologies to promote controllability and efficient and safe exploration of an environment for decision actions – drastically boosting learning effectiveness and interpretability in decision making. Expected outcomes will benefit national cybersecurity by improving our understanding of vulnerabilities and threats involving decision actions, and by ensuring that human feedback and evaluations can help prevent catastrophic events in explorations of dynamic and complex environments.Read moreRead less
New Paradigms for Robust Fitting: Kernelisation and Polyhedral Search. Outliers inevitably exist in visual data due to imperfect data acquisition or preprocessing. To enable computer vision applications that can perform reliably, robust fitting algorithms are necessary to counter the biasing influence of outliers. However, current robust algorithms are unsatisfactory: they are unreliable (due to using randomisation) or too computationally costly (due to using exhaustive search). This project wil ....New Paradigms for Robust Fitting: Kernelisation and Polyhedral Search. Outliers inevitably exist in visual data due to imperfect data acquisition or preprocessing. To enable computer vision applications that can perform reliably, robust fitting algorithms are necessary to counter the biasing influence of outliers. However, current robust algorithms are unsatisfactory: they are unreliable (due to using randomisation) or too computationally costly (due to using exhaustive search). This project will develop new robust algorithms to mitigate these shortcomings. It will do so by investigating two new paradigms of kernelisation and polyhedral search, which offer unprecedented theoretical insights into the problem. The outcomes will contribute towards computer vision applications that are more practical and reliable.Read moreRead less
Collision Avoidance in Shipping Lanes via Intelligent Sensor Data Fusion . This project aims to develop an online maritime traffic monitoring system for reliable collision/contact avoidance that exploits complementary data from high-resolution airborne sensors and surface vessel sensors. Our approach is based on optimal scheduling and fusion of the sensor data and possibly other sources of data to construct a comprehensive dynamic picture of maritime traffic, in real-time. Moreover, the proposed ....Collision Avoidance in Shipping Lanes via Intelligent Sensor Data Fusion . This project aims to develop an online maritime traffic monitoring system for reliable collision/contact avoidance that exploits complementary data from high-resolution airborne sensors and surface vessel sensors. Our approach is based on optimal scheduling and fusion of the sensor data and possibly other sources of data to construct a comprehensive dynamic picture of maritime traffic, in real-time. Moreover, the proposed methodology enables quantification of confidence in the predictions. This will provide ship owners, directly to their vessels and/or at the fleet management centres, information such as weather reports, reliable collision/no-collision warnings and avoidance strategies, on-the-fly. Read moreRead less