Robust speech recognition in realistic hostile environments. Australia leads the world in the adoption of speech recognition technology but sadly lags in the development of the fundamental advances in the area. This research will help propel Australia to the forefront of new innovations in speech recognition technology and contributions to fundamental science. Our project will provide an excellent training ground for graduate students and researchers, with the real possibility of significant com ....Robust speech recognition in realistic hostile environments. Australia leads the world in the adoption of speech recognition technology but sadly lags in the development of the fundamental advances in the area. This research will help propel Australia to the forefront of new innovations in speech recognition technology and contributions to fundamental science. Our project will provide an excellent training ground for graduate students and researchers, with the real possibility of significant commercial benefit to the nation. The deployment of our system in the community will greatly enhance the defence and police forces ability for surveillance and security, and will provide new assistive aids to improve the quality of life and safety for the elderly and disabled.Read moreRead less
Modelling and estimation methods for discrete multi-dimensional systems. Multi-dimensional signal processing plays a role in a variety of application areas, ranging from remote sensing for environmental monitoring and geological mapping, to medical imaging and the automatic control of industrial processes. The success of the project will provide mathematical tools for the advancement of the state-of-the-art in these broad areas.
Optimum Multi-rate Filter Bank Design for Speech Enhancement and Communication Systems. Multi-rate signal processing is gaining more and more importance in signal processing applications such as echo cancellation, microphone arrays, speech enhancement and equalisation. This project is aimed at obtaining high performance and high efficiency multi-rate processing designs by developing appropriate problem formulations based on solid mathematical foundations so that powerful optimisation techniques ....Optimum Multi-rate Filter Bank Design for Speech Enhancement and Communication Systems. Multi-rate signal processing is gaining more and more importance in signal processing applications such as echo cancellation, microphone arrays, speech enhancement and equalisation. This project is aimed at obtaining high performance and high efficiency multi-rate processing designs by developing appropriate problem formulations based on solid mathematical foundations so that powerful optimisation techniques can be applied. The developed multi-rate systems will result in low complexity and low power hardware implementations without significant compromise in performance in each application. Size and cost sensitive of communication devices such as personal data assistants, mobile telephones, hands-free devices, and laptops will benefit greatly from the outcome of the project.Read moreRead less
Convex optimisation for control, signal processing and communication systems. Renewable control of complex systems, signal processing, telecommunication and in general any industries interested in these applications stand to benefit from our research. In particular, the automotive and defence industries stand to benefit from the nonlinear control design aspect of the proposed project outcomes. The
telecommunications industries, on the other hand, benefit from the signal processing and communicat ....Convex optimisation for control, signal processing and communication systems. Renewable control of complex systems, signal processing, telecommunication and in general any industries interested in these applications stand to benefit from our research. In particular, the automotive and defence industries stand to benefit from the nonlinear control design aspect of the proposed project outcomes. The
telecommunications industries, on the other hand, benefit from the signal processing and communications aspects. We also build a core expertise in optimisation and its applications in Australia by training PhD students and Postdoctoral researchers. The research collaborations will cement and maintain the international linkages which will improve applied research in AustraliaRead moreRead less
International collaboration in gravitational wave data analysis, simulations and third generation detectors. The project brings together seven outstanding international researchers into close collaboration with an Australian team to develop new techniques for finding gravitational wave signals in the vast archive of data they have helped to collect, as well as developing and testing theory for improved detectors that operate with sensitivity beyond the limits set by classical physics. The projec ....International collaboration in gravitational wave data analysis, simulations and third generation detectors. The project brings together seven outstanding international researchers into close collaboration with an Australian team to develop new techniques for finding gravitational wave signals in the vast archive of data they have helped to collect, as well as developing and testing theory for improved detectors that operate with sensitivity beyond the limits set by classical physics. The project will utilize a state of the art supercomputer and the superb national facility for high power laser interferometry at Gingin, Western Australia. Read moreRead less
Blind separation of mutually correlated sources. This project is aimed at developing novel techniques for blind separation of mutually correlated sources. The expected outcomes will significantly advance the theory of blind source separation and improve the performance of important practical systems, such as densely deployed sensor networks and wireless video surveillance systems.
Development of a three dimensional audio-visual next generation speech recognition system. To overcome the disadvantages of current Audio-Visual Speech Recognition Systems, we propose a set of robust algorithms in three dimensional computer vision and speech processing. The proposed system will have far-reaching implications in various areas, for example, human-machine interaction for speech recognition in automated dialog systems and voice-to-text conversions.
Real-time signal processing and distributed robotic telescope networking for co-detection of gravitational waves and their optical counterparts. An international collaboration of scientists will employ a global network of telescopes and detectors to search for ripples in space-time. The project will use novel computational tools to study exotic phenomena in the distant Universe.
Analysis of Polynomial Phase Signals with Missing Observations. Many non-stationary signals in radar, physics and communications can be modelled as polynomial phase signals. These signals are often incomplete due to missing observations from intermittent sensor failures, outliers, receiver errors, periodic interference and inaccessibility of data. The aim of this project is to develop robust and computationally efficient methods for recovering such signals from small data sets when there is a la ....Analysis of Polynomial Phase Signals with Missing Observations. Many non-stationary signals in radar, physics and communications can be modelled as polynomial phase signals. These signals are often incomplete due to missing observations from intermittent sensor failures, outliers, receiver errors, periodic interference and inaccessibility of data. The aim of this project is to develop robust and computationally efficient methods for recovering such signals from small data sets when there is a large proportion of missing observations. This will contribute to a conceptual advancement in the field of signal processing and will provide new methods for use in applications such as radar, astrophysics, seismology, vibration analysis and communications.Read moreRead less
Parameter estimation for multi-object systems. Parameter estimation in multi-object system is essential to the application of multi-object filtering to a wider range of practical problems with social and commercial benefits. This project develops the necessary parameter estimation techniques for complete 'plug-and-play' multi-object filtering solutions that facilitates widespread applications.