Bio-inspired speech analysis: Specialised information processing of vocalisations in the auditory brainstem. This project has the potential to benefit bionic ear and hearing aid users through the development of signal processing methods that mimic the amazing abilities of the brain. Speech perception performance by bionic ear users has reached a plateau and these new strategies could produce the breakthrough needed to provide the next increase in performance. The benefit for greater improved hea ....Bio-inspired speech analysis: Specialised information processing of vocalisations in the auditory brainstem. This project has the potential to benefit bionic ear and hearing aid users through the development of signal processing methods that mimic the amazing abilities of the brain. Speech perception performance by bionic ear users has reached a plateau and these new strategies could produce the breakthrough needed to provide the next increase in performance. The benefit for greater improved hearing has enormous benefit and potential for improving the quality of life of the hearing impaired, especially those with severe and profound hearing loss. In addition, the algorithms may provide more robust automatic speech recognition, making this technology more useful in everyday situations; the markets that this would open up are enormous.Read moreRead less
Cognitive Modelling of Computer Games Pidgins. This project develops a pidgin language for use in computer games and models the way human users exploit such languages. It has implications also for computer assisted collaborative work and other educational or entertainment interactive environments like computer games. By developing mini-languages for games environments we can dramatically simplify the speech recognition problem and make recognition robust across different speech cultures and ba ....Cognitive Modelling of Computer Games Pidgins. This project develops a pidgin language for use in computer games and models the way human users exploit such languages. It has implications also for computer assisted collaborative work and other educational or entertainment interactive environments like computer games. By developing mini-languages for games environments we can dramatically simplify the speech recognition problem and make recognition robust across different speech cultures and backgrounds. We use protocol analysis and markup techniques for modelling dialogues between human player and reactive agents in computer games.Read moreRead less
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
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
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
Determinants of Audio-Visual effects in degraded and non-degraded speech. Seeing a speaker's face can affect the perception of their speech in a number of ways. This project proposes a detailed comparison of factors that affect Audio-Visual (AV) facilitation of degraded speech detection and identification. Detection-based tasks should be more sensitive to signal based correlations whereas identification-based effects more sensitive to complementary information. The significance of the current pr ....Determinants of Audio-Visual effects in degraded and non-degraded speech. Seeing a speaker's face can affect the perception of their speech in a number of ways. This project proposes a detailed comparison of factors that affect Audio-Visual (AV) facilitation of degraded speech detection and identification. Detection-based tasks should be more sensitive to signal based correlations whereas identification-based effects more sensitive to complementary information. The significance of the current proposal is that it offers both a strategy and a connected series of experiments for determining key behavioural constraints on AV speech integration. Understanding AV interactions will build links between neurophysiological processes and coherent perception and have important implications for AV application.Read moreRead less
ARC Research Network for Enabling Human Communication. The Human Communication Network promotes interdisciplinary research in speech, language, and sound by and between humans and machines. The network connects leading and emerging researchers across disciplines, exploits previously unrecognised intersections, supports interdisciplinary graduate training and exchanges, provides database storage infrastructure, and consults with industry and government to set, not follow, research agendas. By ge ....ARC Research Network for Enabling Human Communication. The Human Communication Network promotes interdisciplinary research in speech, language, and sound by and between humans and machines. The network connects leading and emerging researchers across disciplines, exploits previously unrecognised intersections, supports interdisciplinary graduate training and exchanges, provides database storage infrastructure, and consults with industry and government to set, not follow, research agendas. By generating an explosion of new approaches and knowledge, the network will build Australia's reputation as a leader in communication science and technology via advances in automatic speech recognition, distress call monitoring, hearing prostheses, web interfaces, and data retrieval and data mining systems.Read moreRead less
ARC Communications Research Network. Building on a strong platform of existing research excellence, the Aim of the Network is to facilitate nation-wide collaborative research, promoting four intersecting research Themes: Mobile and Wireless Communications, Rural Communications, Broadband and Optical Networks, and Fundamentals of Emerging Media. Each Theme is formulated to drive multidisciplinary, innovative research as well as inspire new collaborative initiatives. Four Programs encapsulate the ....ARC Communications Research Network. Building on a strong platform of existing research excellence, the Aim of the Network is to facilitate nation-wide collaborative research, promoting four intersecting research Themes: Mobile and Wireless Communications, Rural Communications, Broadband and Optical Networks, and Fundamentals of Emerging Media. Each Theme is formulated to drive multidisciplinary, innovative research as well as inspire new collaborative initiatives. Four Programs encapsulate the core activities of the Network: Researcher Mobility, Workshops and Conferences, Postgraduate Education, and Knowledge Management Systems. The Network is expected to add significant value to pre-existing investments and raise the profile of Australian telecommunications research.Read moreRead less
Frequency-related features derived from phase spectrum for robust speech recognition. Though the currently available speech recognizers work reasonably well in noise-free environments, their performance deteriorates drastically even in the presence of a small amount of noise. In order to overcome this problem, new frequency-related features are proposed in this project for speech recognition. These features are derived from the phase spectrum of the speech signal, and are expected to be robust t ....Frequency-related features derived from phase spectrum for robust speech recognition. Though the currently available speech recognizers work reasonably well in noise-free environments, their performance deteriorates drastically even in the presence of a small amount of noise. In order to overcome this problem, new frequency-related features are proposed in this project for speech recognition. These features are derived from the phase spectrum of the speech signal, and are expected to be robust to the additive noise distortion. These features will make the speech recognizer less sensitive to noise and will enhance its utility in a number of applications in the telecommunication and business world.Read moreRead less
Fixed and variable-length segment vocoders for very low bitrate speech coding. Reliable and secure voice communication is an important aspect of military and defence operations. In order to reduce the possibility of interception, low power transmitters are normally used for radio communications, where the bandwidth is often very low. Military voice communication, therefore, requires the coding of speech at very low bitrates. Our research proposal aims to develop speech coders that can operate ....Fixed and variable-length segment vocoders for very low bitrate speech coding. Reliable and secure voice communication is an important aspect of military and defence operations. In order to reduce the possibility of interception, low power transmitters are normally used for radio communications, where the bandwidth is often very low. Military voice communication, therefore, requires the coding of speech at very low bitrates. Our research proposal aims to develop speech coders that can operate at lower bitrates and reproduce speech of high quality and intelligibility. This is highly beneficial to the defence forces of Australia as it will permit the use of high-grade encryption technology to improve the security of transmission.Read moreRead less