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
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
A compact microphone array system for outdoor low frequency noise measurements. To investigate the impact of wind farm noise on surrounding communities, the sound level caused by wind turbines must be accurately measured, which sometimes is hard due to wind induced noise and other interference noise. This project aims to propose a novel compact microphone array solution, where the wind induced noise is attenuated by a specially designed windproof shell first, and then the residual wind induced n ....A compact microphone array system for outdoor low frequency noise measurements. To investigate the impact of wind farm noise on surrounding communities, the sound level caused by wind turbines must be accurately measured, which sometimes is hard due to wind induced noise and other interference noise. This project aims to propose a novel compact microphone array solution, where the wind induced noise is attenuated by a specially designed windproof shell first, and then the residual wind induced noise and other interference noise are further filtered out by a specific adaptive noise cancellation algorithm based on the spherical and differential microphone array structure. With the proposed system, the measurement configuration size is expected to be reduced from the current few metres to less than 10 centimetres, and with better accuracy.Read moreRead less
The development of new techniques for partial discharge monitoring and location in high voltage underground power cables. Increased utilization factors have caused a significant increase in the loading of high voltage distribution cables. This increased loading subjects cable insulation to increased stress which can degrade the insulation, cause cable failure and power loss to consumers. On-line cable insulation monitoring is required and partial discharge monitoring in cables provides a viable ....The development of new techniques for partial discharge monitoring and location in high voltage underground power cables. Increased utilization factors have caused a significant increase in the loading of high voltage distribution cables. This increased loading subjects cable insulation to increased stress which can degrade the insulation, cause cable failure and power loss to consumers. On-line cable insulation monitoring is required and partial discharge monitoring in cables provides a viable technique, but technical problems have prevented its application in on-line operation.
This project will develop techniques for such on-line monitoring. High frequency electrical sensors will be used to reduce interference and improve signal levels. Both a coarse alarm and a higher sensitivity monitor will be developed.
Read moreRead less
Vector quantization approaches to nonlinear stochastic estimation. Many problems in health, economics, telecommunications and industrial control can be formulated as estimation problems with uncertain data. This project is aimed at developing a novel class of algorithms aimed at high complexity estimation problems. If successful, the project will provide new approaches to these problems.
Joint modelling and recognition of linguistic and paralinguistic speech information. A new modelling framework will be developed exploiting interdependence between linguistic and paralinguistic cues to improve automatic recognition of emotion-related information. Applications in the high-tech industry include automatic routing of angry telephone customers or pre-suicidal crisis centre callers to specialist operators/clinicians.
Spectral analysis with selective harmonic emphasis. This project lies under ARC research priority area "Frontier Technologies for Building and Transforming Australian Industries". The signal processing algorithms to be developed in this project will be useful in many important practical applications, which include various bio-medical imaging modalities, beamforming, radar, sonar and target tracking using sensor arrays. The idea is to use the prior knowledge to enhance certain desired properties ....Spectral analysis with selective harmonic emphasis. This project lies under ARC research priority area "Frontier Technologies for Building and Transforming Australian Industries". The signal processing algorithms to be developed in this project will be useful in many important practical applications, which include various bio-medical imaging modalities, beamforming, radar, sonar and target tracking using sensor arrays. The idea is to use the prior knowledge to enhance certain desired properties of the algorithms via intelligent processing. In this light the project also lies within the ARC research priority area of "Smart Information use".Read moreRead less
Automatic speech-based assessment of mental state via mobile device. This project aims to create the first mobile, device-based automatic assessment of mental state from acoustic speech. Focusing on novel approaches for eliciting speech, for regression-based scoring of mental state and for longitudinal modelling of speech, the project takes speech processing out of the laboratory and into realistic environments. The project is significant because elicitation approach and longitudinal modelling h ....Automatic speech-based assessment of mental state via mobile device. This project aims to create the first mobile, device-based automatic assessment of mental state from acoustic speech. Focusing on novel approaches for eliciting speech, for regression-based scoring of mental state and for longitudinal modelling of speech, the project takes speech processing out of the laboratory and into realistic environments. The project is significant because elicitation approach and longitudinal modelling have been acknowledged by the research community as challenges that are valuable to investigate, and because conventional regression methods are sub-optimal on ordinal mental state scales. This is significant commercially because mobile devices allow individually tailored, frequent and low-cost mental state assessment. Expected outcomes will include commercial-ready technology, trialled on Australians, accessible to everyone with a mobile device and concentration of Australian research and development capability in a rapidly growing application area.Read moreRead less
Biologically Inspired Binaural Coupling for Selective Machine Hearing. This project aims to investigate biologically-inspired binaural coupling models in the context of the deep learning paradigm by formulating desirable higher level auditory structures as neural network sub-systems. This project expects to generate new knowledge for developing the next generation of robust speech processing systems that are capable of mimicking the selecting listening ability of humans when faced with realistic ....Biologically Inspired Binaural Coupling for Selective Machine Hearing. This project aims to investigate biologically-inspired binaural coupling models in the context of the deep learning paradigm by formulating desirable higher level auditory structures as neural network sub-systems. This project expects to generate new knowledge for developing the next generation of robust speech processing systems that are capable of mimicking the selecting listening ability of humans when faced with realistic noisy speech signals and the ‘cocktail party problem’ using innovative binaural feedback systems. This work should provide significant benefits, including improved voice biometrics and selective auditory attention capabilities in machines.Read moreRead less
Integrating biologically-inspired auditory models into deep learning. This project aims to discover how a biologically inspired auditory model can be tightly integrated into a state-of-the-art deep learning speech processing framework, to model, design and verify a deep learning based auditory model. Voice-based technologies, ranging from cochlear implants to smart homes, are growing at a rapid pace and speech interfaces are being integrated with all aspects of our lives. However, there is a gro ....Integrating biologically-inspired auditory models into deep learning. This project aims to discover how a biologically inspired auditory model can be tightly integrated into a state-of-the-art deep learning speech processing framework, to model, design and verify a deep learning based auditory model. Voice-based technologies, ranging from cochlear implants to smart homes, are growing at a rapid pace and speech interfaces are being integrated with all aspects of our lives. However, there is a growing demand to improve these voice-enabled services, making them more secure and less open to cyber-crime attack by unauthorised users. The project is expected to improve techniques for modelling and automatic processing of speech and audio signals, which should provide significant benefits, including improved voice biometrics and cochlear implants.Read moreRead less