Beamforming with acoustic vector sensors for audio user interfaces. We aim to create new Audio User Interfaces (AUIs) for the automatic separation and annotation of audio from complex sound scenes using acoustic vector sensor beamforming technology. Specifically, we will develop: speech AUIs for noisy, multi-talker, reverberant environments; and sound transcription AUIs for the deaf. Ultimately, users will be able to walk into a room, hold conversations and leave with a searchable, automatically ....Beamforming with acoustic vector sensors for audio user interfaces. We aim to create new Audio User Interfaces (AUIs) for the automatic separation and annotation of audio from complex sound scenes using acoustic vector sensor beamforming technology. Specifically, we will develop: speech AUIs for noisy, multi-talker, reverberant environments; and sound transcription AUIs for the deaf. Ultimately, users will be able to walk into a room, hold conversations and leave with a searchable, automatically-generated transcript of the audio events, tagged with metadata. The application of these technologies will create new possibilities for recording audio in the music, radio, TV industries, and future home based audio communication systems.Read moreRead less
Resource-aware Signal Processing and Control Algorithms for Networked Sensor Systems. Networked sensing and control is an important technology for Australia's future. Applications range from monitoring wildlife habitats to safety management of large civil structures. This project will lead to sustainable engineering solutions for these applications and provide key fundamental performance limits. Beyond the creation of new theory and algorithms, the national and community benefits will include: ....Resource-aware Signal Processing and Control Algorithms for Networked Sensor Systems. Networked sensing and control is an important technology for Australia's future. Applications range from monitoring wildlife habitats to safety management of large civil structures. This project will lead to sustainable engineering solutions for these applications and provide key fundamental performance limits. Beyond the creation of new theory and algorithms, the national and community benefits will include: (i) enhancement of Australia's reputation for innovative Engineering research through quality publications and international collaborations; and (ii) improvement of the research and development capability in the ICT sector through rigorous training of postgraduate students and postdoctoral fellows.Read moreRead less
Fundamentals of active sensor network for damage identification in engineering structures. The development of active sensor network techniques for Australia's vast civil and defence infrastructure will improve operational safety, reduce maintenance costs and extend the residual life of many of our engineered assets. The resulting cost-efficiencies will advantage Australian producers in competitive global markets; our companies will be well placed to produce and install active sensor network tech ....Fundamentals of active sensor network for damage identification in engineering structures. The development of active sensor network techniques for Australia's vast civil and defence infrastructure will improve operational safety, reduce maintenance costs and extend the residual life of many of our engineered assets. The resulting cost-efficiencies will advantage Australian producers in competitive global markets; our companies will be well placed to produce and install active sensor network techniques and to provide training in the associated asset management systems. Australian industry will have a unique opportunity to collaborate with the world-class research networks on emerging areas such as damage diagnosis, prognosis and control, and structural repair.Read moreRead less
Encoding and Communicating Navigable Soundfields. While sound recording is commonplace, it is not currently practical to completely record a sound space such that the experience can be reproduced at a chosen 'listening point'. This is a significant restriction for audio applications in the entertainment, surveillance and virtual/mixed reality areas. The project will research novel and practical solutions to this problem and offers a significant conceptual advance in the transmission of complex a ....Encoding and Communicating Navigable Soundfields. While sound recording is commonplace, it is not currently practical to completely record a sound space such that the experience can be reproduced at a chosen 'listening point'. This is a significant restriction for audio applications in the entertainment, surveillance and virtual/mixed reality areas. The project will research novel and practical solutions to this problem and offers a significant conceptual advance in the transmission of complex audio scenes. This project will build fundamental new technology and IP for Australia in the digital media and audio space, one of the fastest growing sectors of our economy.Read moreRead less
Automatic music feature extraction, classification and annotation. Music is a huge industry currently undergoing a major revolution. The industry is shifting from music-making to music retrieval and its incorporation into a range of products from TV, and film, to music streaming into locations and events, as well as MP3 players and all kinds of electronic devices. This research will support immediate retrieval of music that meets the current industry need, based not just on titles, composers and ....Automatic music feature extraction, classification and annotation. Music is a huge industry currently undergoing a major revolution. The industry is shifting from music-making to music retrieval and its incorporation into a range of products from TV, and film, to music streaming into locations and events, as well as MP3 players and all kinds of electronic devices. This research will support immediate retrieval of music that meets the current industry need, based not just on titles, composers and/or performers, but on the actual properties of the music itself. The knowledge and music processing techniques developed will give Australian music industry an advantage over other countries.Read moreRead less
Certified evaluation of uncertainty in models of dynamical systems. The purpose of this project is to develop methods which will aid engineers to better analyse the accuracy of models created using experimental data. To support the use of the methods, a toolbox with software implementations will also be developed.
Mathematical Foundations of Distributed Radar. Conventional military threats to Australia are large or fast moving objects such as ships and aircraft and conventional radar systems are designed to handle such threats. Recent global political shifts have changed the threats to include objects that are small and slowly moving, such as people, small vehicles and boats. Advances in radar hardware make feasible small, low-powered, devices with inherently reduced performance in comparison to deployed ....Mathematical Foundations of Distributed Radar. Conventional military threats to Australia are large or fast moving objects such as ships and aircraft and conventional radar systems are designed to handle such threats. Recent global political shifts have changed the threats to include objects that are small and slowly moving, such as people, small vehicles and boats. Advances in radar hardware make feasible small, low-powered, devices with inherently reduced performance in comparison to deployed systems. Methods for information integration over a dispersed system of such small devices, design of suitable waveform suites and clever local signal processing algorithms will be developed to achieve the performance improvements the hardware offers, to handle the new threats.Read moreRead less
High-performance computational data-mining techniques for feature detection in complex time series from large-scale, networked plasma experiments. Terabytes of data are gathered from large experimental facilities as complex time-series. Analysis of these data is daunting, especially when they involve high-dimensional spectral or image arrays. We will develop high-performance computational techniques for dimension reduction, efficient data-mining, and experimental control, using as an initial ta ....High-performance computational data-mining techniques for feature detection in complex time series from large-scale, networked plasma experiments. Terabytes of data are gathered from large experimental facilities as complex time-series. Analysis of these data is daunting, especially when they involve high-dimensional spectral or image arrays. We will develop high-performance computational techniques for dimension reduction, efficient data-mining, and experimental control, using as an initial target the H-1NF plasma fusion MNRF at the ANU and its >100 GB/year data stream. The techniques will immediately provide Australian researchers with unique tools for collaboration in international research to develop fusion as a low-emissions source of electricity, and will be applicable to complex time-series analysis in other areas of science, medicine, and defence.Read moreRead less
Networked system identification, estimation and control: performance optimisation under communication and resource constraints. Design and analysis of performance optimised networked system identification, estimation and control algorithms will make the implementation of large scale wireless sensor and actuator networks a distinct possibility, thus contributing to significant technological advances in critical areas such as health care, defence and industrial automation.
Automatic audio segmentation, classification, identification, search and retrieval. The research aims to develop generic tools for automated audio segmentation, classification, identification and search, with lowest possible computational complexity and highest accuracy and speed. The tools will be applicable to audio archive management, search of audio material over WWW and personal archives of music and audio-assisted video analysis. The industry will use the tools for automated broadcast ve ....Automatic audio segmentation, classification, identification, search and retrieval. The research aims to develop generic tools for automated audio segmentation, classification, identification and search, with lowest possible computational complexity and highest accuracy and speed. The tools will be applicable to audio archive management, search of audio material over WWW and personal archives of music and audio-assisted video analysis. The industry will use the tools for automated broadcast verification and identification for copyright surveillance and calculation of royalty payments, aiming to penetrate both Australian and overseas markets. The area of real-time audio scene analysis is in its infancy and the research aims to make significant contributions to this area.Read moreRead less