Improving short utterance based I-vector speaker recognition using source and utterance-duration normalization techniques

A significant amount of speech is typically required for speaker verification system development and evaluation, especially in the presence of large intersession variability. This paper introduces a source and utterance duration normalized linear discriminant analysis (SUN-LDA) approaches to compensate session variability in short-utterance i-vector speaker verification systems. Two variations of SUN-LDA are proposed where normalization techniques are used to capture source variation from both short and full-length development i-vectors, one based upon pooling (SUN-LDA-pooled) and the other on concatenation (SUN-LDA-concat) across the duration and source-dependent session variation. Both the SUN-LDA-pooled and SUN-LDA-concat techniques are shown to provide improvement over traditional LDA on NIST 08 truncated 10sec-10sec evaluation conditions, with the highest improvement obtained with the SUN-LDA-concat technique achieving a relative improvement of 8% in EER for mis-matched conditions and over 3% for matched conditions over traditional LDA approaches.

User expertise in contemporary information systems : conceptualization, measurement and application

This research proposes a method for identifying user expertise in contemporary Information Systems (IS). It also proposes and develops a model for evaluating expertise. The aim of this study was to offer a common instrument that addresses the requirements of a contemporary Information System in a holistic way. This study demonstrates the application of the expertise construct in Information System evaluations, and shows that users of different expertise levels evaluate systems differently.

Submission to expert panel on constitutional recognition of Indigenous people

Submission recommended addition of a new 'self-enacting' preamble and enacting words to the Commownealth Constitution, and replacement of the 'race power' by a series of more specific powers relating to the recognition of native title and laws of the indigenous people.

Measurement, modelling and capacity analysis for novel, fixed multi-user single-antenna MIMO-OFDM system, in rural environments

High-speed broadband internet access is widely recognised as a catalyst to social and economic development. However, the provision of broadband Internet services with the existing solutions to rural population, scattered over an extensive geographical area, remains both an economic and technical challenge. As a feasible solution, the Commonwealth Scientific and Industrial Research Organization (CSIRO) proposed a highly spectrally efficient, innovative and cost-effective fixed wireless broadband access technology, which uses analogue TV frequency spectrum and Multi-User MIMO (MUMIMO) technology with Orthogonal-Frequency-Division-Multiplexing (OFDM). MIMO systems have emerged as a promising solution for the increasing demand of higher data rates, better quality of service, and higher network capacity. However, the performance of MIMO systems can be significantly affected by different types of propagation environments e.g., indoor, outdoor urban, or outdoor rural and operating frequencies. For instance, large spectral efficiencies associated with MIMO systems, which assume a rich scattering environment in urban environments, may not be valid for all propagation environments, such as outdoor rural environments, due to the presence of less scatterer densities. Since this is the first time a MU-MIMO-OFDM fixed broadband wireless access solution is deployed in a rural environment, questions from both theoretical and practical standpoints arise; For example, what capacity gains are available for the proposed solution under realistic rural propagation conditions?. Currently, no comprehensive channel measurement and capacity analysis results are available for MU-MIMO-OFDM fixed broadband wireless access systems which employ large scale multiple antennas at the Access Point (AP) and analogue TV frequency spectrum in rural environments. Moreover, according to the literature, no deterministic MU-MIMO channel models exist that define rural wireless channels by accounting for terrain effects. This thesis fills the aforementioned knowledge gaps with channel measurements, channel modeling and comprehensive capacity analysis for MU-MIMO-OFDM fixed wireless broadband access systems in rural environments. For the first time, channel measurements were conducted in a rural farmland near Smithton, Tasmania using CSIRO's broadband wireless access solution. A novel deterministic MU-MIMO-OFDM channel model, which can be used for accurate performance prediction of rural MUMIMO channels with dominant Line-of-Sight (LoS) paths, was developed under this research. Results show that the proposed solution can achieve 43.7 bits/s/Hz at a Signal-to- Noise Ratio (SNR) of 20 dB in rural environments. Based on channel measurement results, this thesis verifies that the deterministic channel model accurately predicts channel capacity in rural environments with a Root Mean Square (RMS) error of 0.18 bits/s/Hz. Moreover, this study presents a comprehensive capacity analysis of rural MU-MIMOOFDM channels using experimental, simulated and theoretical models. Based on the validated deterministic model, further investigations on channel capacity and the eects of capacity variation, with different user distribution angles (θ) around the AP, were analysed. For instance, when SNR = 20dB, the capacity increases from 15.5 bits/s/Hz to 43.7 bits/s/Hz as θ increases from 10° to 360°. Strategies to mitigate these capacity degradation effects are also presented by employing a suitable user grouping method. Outcomes of this thesis have already been used by CSIRO scientists to determine optimum user distribution angles around the AP, and are of great significance for researchers and MU-MUMO-OFDM system developers to understand the advantages and potential capacity gains of MU-MIMO systems in rural environments. Also, results of this study are useful to further improve the performance of MU-MIMO-OFDM systems in rural environments. Ultimately, this knowledge contribution will be useful in delivering efficient, cost-effective high-speed wireless broadband systems that are tailor-made for rural environments, thus, improving the quality of life and economic prosperity of rural populations.

Sequential decision fusion of multibiometrics applied to text-dependent speaker verification for controlled errors

Reliability of the performance of biometric identity verification systems remains a significant challenge. Individual biometric samples of the same person (identity class) are not identical at each presentation and performance degradation arises from intra-class variability and inter-class similarity. These limitations lead to false accepts and false rejects that are dependent. It is therefore difficult to reduce the rate of one type of error without increasing the other. The focus of this dissertation is to investigate a method based on classifier fusion techniques to better control the trade-off between the verification errors using text-dependent speaker verification as the test platform. A sequential classifier fusion architecture that integrates multi-instance and multisample fusion schemes is proposed. This fusion method enables a controlled trade-off between false alarms and false rejects. For statistically independent classifier decisions, analytical expressions for each type of verification error are derived using base classifier performances. As this assumption may not be always valid, these expressions are modified to incorporate the correlation between statistically dependent decisions from clients and impostors. The architecture is empirically evaluated by applying the proposed architecture for text dependent speaker verification using the Hidden Markov Model based digit dependent speaker models in each stage with multiple attempts for each digit utterance. The trade-off between the verification errors is controlled using the parameters, number of decision stages (instances) and the number of attempts at each decision stage (samples), fine-tuned on evaluation/tune set. The statistical validation of the derived expressions for error estimates is evaluated on test data. The performance of the sequential method is further demonstrated to depend on the order of the combination of digits (instances) and the nature of repetitive attempts (samples). The false rejection and false acceptance rates for proposed fusion are estimated using the base classifier performances, the variance in correlation between classifier decisions and the sequence of classifiers with favourable dependence selected using the 'Sequential Error Ratio' criteria. The error rates are better estimated by incorporating user-dependent (such as speaker-dependent thresholds and speaker-specific digit combinations) and class-dependent (such as clientimpostor dependent favourable combinations and class-error based threshold estimation) information. The proposed architecture is desirable in most of the speaker verification applications such as remote authentication, telephone and internet shopping applications. The tuning of parameters - the number of instances and samples - serve both the security and user convenience requirements of speaker-specific verification. The architecture investigated here is applicable to verification using other biometric modalities such as handwriting, fingerprints and key strokes.

Copyright in patent specifications and prior art documents: Addressing legitimate rights of user

One of the recent Raising the Bar amendments has removed impediments imposed by copyright law that may have limited the uses to which IP Australia and members of the public could have lawfully put patent specifications without seeking permission from the copyright owner. What the amendment does not do, however, is extend the same protections to those who wish to use prior art documents in ways that benefit the patent system and further the public interest.

A novel representation of bioacoustic events for content-based search in field audio data

Bioacoustic data can provide an important base for environmental monitoring. To explore a large amount of field recordings collected, an automated similarity search algorithm is presented in this paper. A region of an audio defined by frequency and time bounds is provided by a user; the content of the region is used to construct a query. In the retrieving process, our algorithm will automatically scan through recordings to search for similar regions. In detail, we present a feature extraction approach based on the visual content of vocalisations – in this case ridges, and develop a generic regional representation of vocalisations for indexing. Our feature extraction method works best for bird vocalisations showing ridge characteristics. The regional representation method allows the content of an arbitrary region of a continuous recording to be described in a compressed format.

User-centred study on quality of mobile video services

Mobile video, as an emerging market and a promising research field, has attracted much attention from both industry and researchers. Considering the quality of user-experience as the crux of mobile video services, this chapter aims to provide a guide to user-centered studies of mobile video quality. This will benefit future research in better understanding user needs and experiences, designing effective research, and providing solid solutions to improve the quality of mobile video. This chapter is organized in three main parts: (1) a review of recent user studies from the perspectives of research focuses, user study methods, and data analysis methods; (2) an example of conducting a user study of mobile video research, together with the discussion on a series of relative issues, such as participants, materials and devices, study procedure, and analysis results, and; (3) a conclusion with an open discussion about challenges and opportunities in mobile video related research, and associated potential future improvements.

Sleepiness : how a biological drive can influence other risky road user behaviours

The Safe System approach to road safety utilises a holistic view of the interactions among vehicles, roads and road users. Yet, the contribution of each of these factors to crashes is vastly different. The role of road users is widely acknowledged as an overwhelming contributor to road crashes. Substantial gains have been made with improvements to vehicle and roads over a number of years. However, improvements of the road user’s behaviour has been (in some cases) less substantial. A road user behaviour that is relatively unregulated is driver sleepiness, which is part of the ‘fatal five’ of risky road user behaviours. The effect of sleepiness is ubiquitous – sleepiness is a state that most, if not all drivers on our roads has experienced, and is habitually exposed to. The quality and quantity of daily sleep is integral to our level of neurobehavioural performance during wakefulness and as such can have a compounding effect on a number of other risky driving behaviours. This paper will discuss the potential influence of sleepiness as an interceding factor for a number of risky driving behaviours. Little effort has been given to increasing awareness of the deleterious and wide ranging effects that sleepiness has on road safety. Given the wide ranging influence of sleepiness, improvements of ‘sleep health’ as a protective factor at the community or individual level could lead to significant reductions in road trauma and increases of general well being. A discussion of potential actions to reduce sleepiness is required if reductions of road trauma are to continue.

Timed Probabilistic Automaton : a bridge between Raven and Song Scope for automatic species recognition

Raven and Song Scope are two automated sound anal-ysis tools based on machine learning technique for en-vironmental monitoring. Many research works have been conducted upon them, however, no or rare explo-ration mentions about the performance and comparison between them. This paper investigates the comparisons from six aspects: theory, software interface, ease of use, detection targets, detection accuracy, and potential application. Through deep exploration one critical gap is identified that there is a lack of approach to detect both syllables and call structures, since Raven only aims to detect syllables while Song Scope targets call structures. Therefore, a Timed Probabilistic Automata (TPA) system is proposed which separates syllables first and clusters them into complex structures after.

Identifying the unknown in user space memory

This thesis is a study of how the contents of volatile memory on the Windows operating system can be better understood and utilised for the purposes of digital forensic investigations. It proposes several techniques to improve the analysis of memory, with a focus on improving the detection of unknown code such as malware. These contributions allow the creation of a more complete reconstruction of the state of a computer at acquisition time, including whether or not the computer has been infected by malicious code.

Comparison of Motorists’ and Cyclists’ perception of bicycle safety

Increasing the modal share of public transit systems has become paramount in aiding the reduction on the excessive reliance of personal motor vehicles. More so the need to increase the share of active modes of transport such as the use of bicycles, therefore there is an ever increasing need to use bicycles both on shared pedestrian paths and on-road cycling. The risk to cyclist, or consequently the perception of the risk from both cyclists and motorists alike, is an important factor to increase the use of this transport mode. This paper investigates perception of bicycle safety by conducting a survey and analysing the survey data to understand how participants with different backgrounds perceive the risks of cycling for transport. Contributing factors to people’s perception of bicycle safety were identified and compared across different road user groups, based upon which recommendations were made on how to improve bicycle safety.

The multi-platform user engagement and data visualisation tool

The ability to identify and assess user engagement with transmedia productions is vital to the success of individual projects and the sustainability of this mode of media production as a whole. It is essential that industry players have access to tools and methodologies that offer the most complete and accurate picture of how audiences/users engage with their productions and which assets generate the most valuable returns of investment. Drawing upon research conducted with Hoodlum Entertainment, a Brisbane-based transmedia producer, this project involved an initial assessment of the way engagement tends to be understood, why standard web analytics tools are ill-suited to measuring it, how a customised tool could offer solutions, and why this question of measuring engagement is so vital to the future of transmedia as a sustainable industry. Working with data provided by Hoodlum Entertainment and Foxtel Marketing, the outcome of the study was a prototype for a custom data visualisation tool that allowed access, manipulation and presentation of user engagement data, both historic and predictive. The prototyped interfaces demonstrate how the visualization tool would collect and organise data specific to multiplatform projects by aggregating data across a number of platform reporting tools. Such a tool is designed to encompass not only platforms developed by the transmedia producer but also sites developed by fans. This visualisation tool accounted for multiplatform experience projects whose top level is comprised of people, platforms and content. People include characters, actors, audience, distributors and creators. Platforms include television, Facebook and other relevant social networks, literature, cinema and other media that might be included in the multiplatform experience. Content refers to discreet media texts employed within the platform, such as tweet, a You Tube video, a Facebook post, an email, a television episode, etc. Core content is produced by the creators’ multiplatform experiences to advance the narrative, while complimentary content generated by audience members offers further contributions to the experience. Equally important is the timing with which the components of the experience are introduced and how they interact with and impact upon each other. Being able to combine, filter and sort these elements in multiple ways we can better understand the value of certain components of a project. It also offers insights into the relationship between the timing of the release of components and user activity associated with them, which further highlights the efficacy (or, indeed, failure) of assets as catalysts for engagement. In collaboration with Hoodlum we have developed a number of design scenarios experimenting with the ways in which data can be visualised and manipulated to tell a more refined story about the value of user engagement with certain project components and activities. This experimentation will serve as the basis for future research.

Channel tracking in SDMA-based multi-user MIMO-OFDM communications systems

Capacity of current and future high data rate wireless communications depend significantly on how well changes in the wireless channel are predicted and tracked. Generally, this can be estimated by transmitting known symbols. However, this increases overheads if the channel varies over time. Given today’s bandwidth demand and the increased necessity for mobile wireless devices, the contributions of this research are very significant. This study has developed a novel and efficient channel tracking algorithm that can recursively update the channel estimation for wireless broadband communications reducing overheads, therefore increasing the speed of wireless communication systems.