How, What and Who in Human Communication: Movement of Face and Voice. The aim of this project is to identify the essential characteristics of tone, affect, and identity from face and voice using a combination of signal processing, biological, and behavioural techniques in order to develop a comprehensive model of auditory-visual speech processing and communication. This research will significantly improve understanding of the basis of auditory-visual perception and production in tonal languages ....How, What and Who in Human Communication: Movement of Face and Voice. The aim of this project is to identify the essential characteristics of tone, affect, and identity from face and voice using a combination of signal processing, biological, and behavioural techniques in order to develop a comprehensive model of auditory-visual speech processing and communication. This research will significantly improve understanding of the basis of auditory-visual perception and production in tonal languages and in affective communication, facilitate links between neurophysiological processes and auditory-visual speech processing; and contribute to applications in automatic person recognition, automatic speech recognition, text-to-speech systems, and talking head aids for the hearing impaired.Read moreRead less
Special Research Initiatives - Grant ID: SR0354596
Funder
Australian Research Council
Funding Amount
$20,000.00
Summary
Perception and Action in Auditory Scenes (PAAS): Neural, Behavioural, Computational and Mechanical Systems. Auditory scenes are temporal and ephemeral yet pervasively influence human life. How humans negotiate such scenes has not been solved, a fact highlighted by attempts to build machines to respond to speech, warnings etc., in real-world situations with room reverberation, different talkers, and background noise. No one discipline can solve such problems. In this network outstanding researche ....Perception and Action in Auditory Scenes (PAAS): Neural, Behavioural, Computational and Mechanical Systems. Auditory scenes are temporal and ephemeral yet pervasively influence human life. How humans negotiate such scenes has not been solved, a fact highlighted by attempts to build machines to respond to speech, warnings etc., in real-world situations with room reverberation, different talkers, and background noise. No one discipline can solve such problems. In this network outstanding researchers from physical, medical, human, and social sciences with interests in speech, music and audition will provide insights into how humans and machines localize, recognize, interpret and produce auditory events, and advance frontier technologies, e.g., automatic speech recognition, hearing prostheses, auditory monitoring/warning systems.Read moreRead less
Discovery Early Career Researcher Award - Grant ID: DE200101100
Funder
Australian Research Council
Funding Amount
$425,613.00
Summary
Towards Robotic Empathy: A human centred approach to future AI machines. The project aims to equip future robots with empathy by developing computational models which can leverage from verbal and non-verbal cues. With recent advances in artificial intelligence research, robots now have better cognitive and function skills, but they lack socio-emotional skills. Since these robots are expected to provide assistance to humans across different domains including rehabilitation, education and health c ....Towards Robotic Empathy: A human centred approach to future AI machines. The project aims to equip future robots with empathy by developing computational models which can leverage from verbal and non-verbal cues. With recent advances in artificial intelligence research, robots now have better cognitive and function skills, but they lack socio-emotional skills. Since these robots are expected to provide assistance to humans across different domains including rehabilitation, education and health care, empowering them with empathetic abilities is important for their success. The project will advance fundamental research in machine learning, affective computing and artificial intelligence to model human behavior, personality traits and emotions for an empathetic human-robot interaction.Read moreRead less
Improving the specificity of affective computing via multimodal analysis. This project aims to develop multimodal affective sensing techniques that can sense very subtle expressions in human moods and emotions. Much research in affective computing has investigated ways to improve the sensitivity of affect sensing approaches, resulting in more accurate estimates of affective states such as emotions or mood. What remains unsolved so far is the issue of specificity. This project will address this i ....Improving the specificity of affective computing via multimodal analysis. This project aims to develop multimodal affective sensing techniques that can sense very subtle expressions in human moods and emotions. Much research in affective computing has investigated ways to improve the sensitivity of affect sensing approaches, resulting in more accurate estimates of affective states such as emotions or mood. What remains unsolved so far is the issue of specificity. This project will address this issue through novel analyses of very subtle cues in facial and vocal expressions of affect embedded in a multimodal deep learning framework. Current approaches can successfully assist in binary classification tasks. This project will tackle the much more difficult problem of developing advanced affective sensing technology to simultaneously handle homogeneous and heterogeneous affect classes as well as continuous range estimates of affect intensity.Read moreRead less
Assistive technologies for Autism support. Growing numbers of children are diagnosed with Autism Spectrum Disorder, leading to a massive financial burden on educational, medical and social service systems. This project aims to construct technological solutions to ease this cost with software frameworks for both children and parents. These novel tools and techniques address key issues: personalisation of early intervention, extension of interventions in alternate contexts, and parental support th ....Assistive technologies for Autism support. Growing numbers of children are diagnosed with Autism Spectrum Disorder, leading to a massive financial burden on educational, medical and social service systems. This project aims to construct technological solutions to ease this cost with software frameworks for both children and parents. These novel tools and techniques address key issues: personalisation of early intervention, extension of interventions in alternate contexts, and parental support through analysis of social media. The outcomes aim to include algorithms and prototype applications for flexible early intervention and support for parents and carers, including evaluation of the developed tools in real-world settings.Read moreRead less
Finding and exploiting interesting paths in multidimensional information spaces. This project will invent a new approach for searching within a large complex information space, finding interesting paths between points within the space, visualising the results, and supporting rich, human-centric user interaction with queries and results. This project will embody these techniques in a novel, internet-scale framework to support rapid development of large path search and visualisation applications. ....Finding and exploiting interesting paths in multidimensional information spaces. This project will invent a new approach for searching within a large complex information space, finding interesting paths between points within the space, visualising the results, and supporting rich, human-centric user interaction with queries and results. This project will embody these techniques in a novel, internet-scale framework to support rapid development of large path search and visualisation applications. Evaluation will be via development of several exemplar applications. The techniques and framework will be applicable to a broad range of economically important problems in areas as diverse as health, travel, scientific publication search, product marketing and software engineering.Read moreRead less
A Scalable Theory of Behavior Composition for Practical Engineering Models of Human Performance. Minimizing human error and maximizing human performance is a major design goal in safety critical systems. The development of methods for affordable human performance modeling has widespread applicability for evaluating user-system interfaces. The compositional method explored here has been shown to make accurate predictions reduce model development time by an order of magnitude. Large safety critica ....A Scalable Theory of Behavior Composition for Practical Engineering Models of Human Performance. Minimizing human error and maximizing human performance is a major design goal in safety critical systems. The development of methods for affordable human performance modeling has widespread applicability for evaluating user-system interfaces. The compositional method explored here has been shown to make accurate predictions reduce model development time by an order of magnitude. Large safety critical applications, such as military or air traffic control systems, would benefit greatly. The proposed work tests whether the compositional methods will scale to more complex domains. The work will be coordinated with Australian industry, academia, and government research efforts.Read moreRead less
Development of a computational model for the prediction of mental workload in air traffic control. The aim of the project is to develop a computational model that can measure the flow of traffic through an air sector, and predict the level of workload that an air traffic controller will experience, as well as the overall risk of breakdowns in separation between aircaft. The purpose is to develop a tool that can be used for the purposes of risk analysis and scenario planning. This is a multidisci ....Development of a computational model for the prediction of mental workload in air traffic control. The aim of the project is to develop a computational model that can measure the flow of traffic through an air sector, and predict the level of workload that an air traffic controller will experience, as well as the overall risk of breakdowns in separation between aircaft. The purpose is to develop a tool that can be used for the purposes of risk analysis and scenario planning. This is a multidisciplinary project, integrating recent models of human memory and reasoning, with formal methods for the analysis of human-computer systems. The project will advance our understanding of human memory and reasoning in complex real-world systems.Read moreRead less
Special Research Initiatives - Grant ID: SR0567196
Funder
Australian Research Council
Funding Amount
$55,000.00
Summary
Improved early detection of breast cancer enabled by grid-computing and advanced modelling and visualisation of MR images. This project will investigate the utility of grid computing in the detection of breast cancer from magnetic resonance (MR) images. The large quantity of data acquired using MR imaging is difficult for clinicians to review and the cost of missed or incorrect detection is high. To provide rapid visualisation and assessment of the acquired data, grid computing will be used in c ....Improved early detection of breast cancer enabled by grid-computing and advanced modelling and visualisation of MR images. This project will investigate the utility of grid computing in the detection of breast cancer from magnetic resonance (MR) images. The large quantity of data acquired using MR imaging is difficult for clinicians to review and the cost of missed or incorrect detection is high. To provide rapid visualisation and assessment of the acquired data, grid computing will be used in conjunction with interactive visualisation with haptic feedback. Grid computing experience and haptic device expertise will be achieved via Swedish collaborators. The successful outcome of this project will be software for the production of 3D colour-coded breast images in which suspicious regions are highlighted and can be physically interrogated using the haptic device.Read moreRead less
Computational tools to analyse and exploit the social media revolution. We aim to create technologies to analyse social media communities, which are rapidly growing in reach, complexity, and content produced and shared. Powerful techniques to tap this resource will lead to commercial outcomes for marketing and search industries, alongside deeper insight into the cultural and social impact of this Internet revolution.