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
Enhanced Multilingual Speaker Recognition through the Incorporation of High-Level Features, Late Fusion and Discriminative Classification Methods. The development of robust multilingual speaker recognition systems will benefit the community through the elimination of fraud incurred by financial institutions and customers by enabling several person authentication applications such as: voice based signatures and document issuance; credit card verification by voice and secure over-the-phone financi ....Enhanced Multilingual Speaker Recognition through the Incorporation of High-Level Features, Late Fusion and Discriminative Classification Methods. The development of robust multilingual speaker recognition systems will benefit the community through the elimination of fraud incurred by financial institutions and customers by enabling several person authentication applications such as: voice based signatures and document issuance; credit card verification by voice and secure over-the-phone financial transactions. The technology will also assist in the protection of the community and safeguard Australia by enabling the implementation of the following: suspect identification using voice print; national security measures for combating terrorism by using voice to locate and track terrorists; preemptive criminal activity counter-measures; surveillance and secure building access by voice.Read moreRead less
Robust speaker recognition with reduced utterance duration and intersession variability. The development of robust and accurate speaker recognition systems will enable secure person authentication in over-the-phone financial transactions and benefit the community through the elimination of identity fraud incurred by customers and financial institutions. The technology will also assist in safeguarding Australia by enabling the implementation of suspect identification using voice and security meas ....Robust speaker recognition with reduced utterance duration and intersession variability. The development of robust and accurate speaker recognition systems will enable secure person authentication in over-the-phone financial transactions and benefit the community through the elimination of identity fraud incurred by customers and financial institutions. The technology will also assist in safeguarding Australia by enabling the implementation of suspect identification using voice and security measures for combating terrorism by using voice to locate and track terrorists. Our research at QUT Speech Research Lab is at the forefront of development in this field and will provide Australia with a technological advantage in the rapidly evolving global market for speaker recognition technology for person authentication applications.Read moreRead less
Robust Automatic Speaker Diarisation of Audio Documents by Exploiting Prior Sources of Information. Speaker Diarisation, the task of determining who spoke when, is a technology fundamental in deriving intelligent information from audio and multimedia resources. The requirement for efficient and accurate Speaker Diarisation systems, portable across different domains is heightened by the explosive growth of audio and multimedia archives online and throughout the world. This research will provide t ....Robust Automatic Speaker Diarisation of Audio Documents by Exploiting Prior Sources of Information. Speaker Diarisation, the task of determining who spoke when, is a technology fundamental in deriving intelligent information from audio and multimedia resources. The requirement for efficient and accurate Speaker Diarisation systems, portable across different domains is heightened by the explosive growth of audio and multimedia archives online and throughout the world. This research will provide the foundation for a commercial service of automatic Speaker Diarisation to be developed, growing Australia's impact on the information and communications technology (ICT) sector. The outcome of this research will also assist in the tracking of terrorist and unlawful activity by enabling effective intelligence gathering from different audio sources.Read moreRead less
Adaptive learning of spatiotemporal patterns: Development of multi-layer spiking neuron networks using Hebbian and competitive learning. The aim of this project is to develop a method for recognising patterns that change in time. The development of a reliable method that is fast and robust to noise will have wide application in many areas, especially computer speech recognition where timing plays a crucial role. Building-blocks similar to those in the brain (spiking neurons) will be used. Aut ....Adaptive learning of spatiotemporal patterns: Development of multi-layer spiking neuron networks using Hebbian and competitive learning. The aim of this project is to develop a method for recognising patterns that change in time. The development of a reliable method that is fast and robust to noise will have wide application in many areas, especially computer speech recognition where timing plays a crucial role. Building-blocks similar to those in the brain (spiking neurons) will be used. Automatic techniques will be used to teach groups of spiking neurons the differences between sequences of events by adjusting connections between them. The significance of this approach is that it captures information about timing that is missed in existing techniques.Read moreRead less
Adaptive learning in networks of spiking neurons for recognising patterns that change with time. The aim of this project is to develop a method for recognising patterns that change with time. Building-blocks similar to those in the brain (spiking neurons) will be used. Automatic techniques will be developed to teach groups of spiking neurons the differences between sequences of events by adjusting connections between neurons. The significance of this approach is that it captures information abou ....Adaptive learning in networks of spiking neurons for recognising patterns that change with time. The aim of this project is to develop a method for recognising patterns that change with time. Building-blocks similar to those in the brain (spiking neurons) will be used. Automatic techniques will be developed to teach groups of spiking neurons the differences between sequences of events by adjusting connections between neurons. The significance of this approach is that it captures information about timing that is missed in existing techniques. The development of a reliable method that is fast and robust to noise will have wide application in many areas, especially computer speech recognition where timing plays a crucial role.Read moreRead less
Temporal Pattern Learning and Recognition in Neural Systems. This project is relevant to the National Research Priority area of Frontier Technologies and addresses fundamental cross-disciplinary issues of how neural systems learn patterns that change with time, which is at the cutting edge of intelligent processing systems. Applications are in rapidly growing fields of automatic speech processing, robotics, machine learning and intelligent systems, all with applications in areas of economic impo ....Temporal Pattern Learning and Recognition in Neural Systems. This project is relevant to the National Research Priority area of Frontier Technologies and addresses fundamental cross-disciplinary issues of how neural systems learn patterns that change with time, which is at the cutting edge of intelligent processing systems. Applications are in rapidly growing fields of automatic speech processing, robotics, machine learning and intelligent systems, all with applications in areas of economic importance. Application to cochlear implant speech processing will provide benefit for the hearing impaired. The project will provide students with training at an international level within Australia, thus helping ensure Australia maintains and extends its science and technology base into the future.Read moreRead less
Asymptotic Geometric Analysis and Machine Learning. Phenomena in large dimensions appear in a number of domains of Mathematics and adjacent domains of science (e.g. Computer Science), dealing with functions of infinitely growing number of parameters. Here, we focus on several questions naturally linked to Asymptotic Geometric Analysis which have natural applications to Statistical Learning Theory. We intend to use geometric, probabilistic and combinatorial methods to investigate these problems, ....Asymptotic Geometric Analysis and Machine Learning. Phenomena in large dimensions appear in a number of domains of Mathematics and adjacent domains of science (e.g. Computer Science), dealing with functions of infinitely growing number of parameters. Here, we focus on several questions naturally linked to Asymptotic Geometric Analysis which have natural applications to Statistical Learning Theory. We intend to use geometric, probabilistic and combinatorial methods to investigate these problems, with an emphasis on modern tools in Empirical Processes Theory and the theory of Random Matrices.Read moreRead less
Taming media for the masses: Computational frameworks for intelligent digital media capture, management, and sharing. The core issues tackled in this project are learning, recognition and application of semantics in multimedia data and the context of its creation and use - a foundational issue in pattern recognition with many applications. The project is part of the Institute for Multi-sensor Processing and Content Analysis whose aim is to tackle technical issues in large scale pattern recogniti ....Taming media for the masses: Computational frameworks for intelligent digital media capture, management, and sharing. The core issues tackled in this project are learning, recognition and application of semantics in multimedia data and the context of its creation and use - a foundational issue in pattern recognition with many applications. The project is part of the Institute for Multi-sensor Processing and Content Analysis whose aim is to tackle technical issues in large scale pattern recognition. By developing scalable and robust techniques to extract information from large scale multi-modal data, the applications include large scale surveillance systems from multi-modal data (e.g. airport security, smart homes for the aged), context-aware devices, and the next generation of media creation and repurposing tools - a fast-growing sector of the economy.Read moreRead less
Bridging the semantic gap for building effective content management systems: Computational media aesthetics. This project focuses on video abstraction and aims to bridge the semantic gap between the simplicity of available visual features and the richness of user descriptions. We examine how visual and aural techniques are brought together to influence the engagement of audience in a story portrayal. The major outcome will be a computational framework for extracting the semantics associated wi ....Bridging the semantic gap for building effective content management systems: Computational media aesthetics. This project focuses on video abstraction and aims to bridge the semantic gap between the simplicity of available visual features and the richness of user descriptions. We examine how visual and aural techniques are brought together to influence the engagement of audience in a story portrayal. The major outcome will be a computational framework for extracting the semantics associated with audiovisual elements in television/film, and scalable software tools that can rapidly and consistently analyse media along various aesthetic dimensions. It will allow for high-level annotation of media and the building of more effective content management systems with enhanced user querying capabilities.Read moreRead less