Minimising speaker verification utterance length through confidence based early verification decisions

This paper presents a novel approach of estimating the confidence interval of speaker verification scores. This approach is utilised to minimise the utterance lengths required in order to produce a confident verification decision. The confidence estimation method is also extended to address both the problem of high correlation in consecutive frame scores, and robustness with very limited training samples. The proposed technique achieves a drastic reduction in the typical data requirements for producing confident decisions in an automatic speaker verification system. When evaluated on the NIST 2005 SRE, the early verification decision method demonstrates that an average of 5–10 seconds of speech is sufficient to produce verification rates approaching those achieved previously using an average in excess of 100 seconds of speech.

A novel nonrepudiable threshold multi-proxy multi-signature scheme with shared verification

Tzeng et al. proposed a new threshold multi-proxy multi-signature scheme with threshold verification. In their scheme, a subset of original signers authenticates a designated proxy group to sign on behalf of the original group. A message m has to be signed by a subset of proxy signers who can represent the proxy group. Then, the proxy signature is sent to the verifier group. A subset of verifiers in the verifier group can also represent the group to authenticate the proxy signature. Subsequently, there are two improved schemes to eliminate the security leak of Tzeng et al.’s scheme. In this paper, we have pointed out the security leakage of the three schemes and further proposed a novel threshold multi-proxy multi-signature scheme with threshold verification.

Treadmill adaptation and verification of self-selected walking speed : a protocol for children

The term self-selected (i.e., individual or comfortable walking pace or speed) is commonly used in the literature (Frost, Dowling, Bar-Or, & Dyson, 1997; Jeng, Liao, Lai, & Hou, 1997; Wergel-Kolmert & Wohlfart, 1999; Maltais, Bar-Or, Pienynowski, & Galea, 2003; Browning & Kram, 2005; Browning, Baker, Herron, & Kram, 2006; Hills, Byrne, Wearing, & Armstrong, 2006) and is identified as the most efficient walking speed, with increased efficiency defined by lower oxygen uptake (VO^sub 2^) per unit mechanical work (Hoyt & Taylor, 1981; Taylor, Heglund, & Maloiy, 1982; Hreljac, 1993). [...] assessing individual and group differences in metabolic energy expenditure using oxygen uptake requires individuals to be comfortable with, and able to accommodate to, the equipment.

Modeling and Verification of Privacy Enhancing Protocols

Privacy enhancing protocols (PEPs) are a family of protocols that allow secure exchange and management of sensitive user information. They are important in preserving users’ privacy in today’s open environment. Proof of the correctness of PEPs is necessary before they can be deployed. However, the traditional provable security approach, though well established for verifying cryptographic primitives, is not applicable to PEPs. We apply the formal method of Coloured Petri Nets (CPNs) to construct an executable specification of a representative PEP, namely the Private Information Escrow Bound to Multiple Conditions Protocol (PIEMCP). Formal semantics of the CPN specification allow us to reason about various security properties of PIEMCP using state space analysis techniques. This investigation provides us with preliminary insights for modeling and verification of PEPs in general, demonstrating the benefit of applying the CPN-based formal approach to proving the correctness of PEPs.

Internetalisation : the Internet's influence on international market growth in the firm's outward internationalisation process

It has been suggested that the Internet is the most significant driver of international trade in recent years to the extent that the term =internetalisation‘ has been coined (Bell, Deans, Ibbotson & Sinkovics, 2001; Buttriss & Wilkinson, 2003). This term is used to describe the Internet‘s affect on the internationalisation process of the firm. Consequently, researchers have argued that the internationalisation process of the firm has altered due to the Internet, hence is in need of further investigation. However, as there is limited research and understanding, ambiguity remains in how the Internet has influenced international market growth. Thus, the purpose of this study was to explore how the Internet influences firms‘ internationalisation process, specifically, international market growth. To this end, Internet marketing and international market growth theories are used to illuminate this ambiguity in the body of knowledge. Thus, the research problem =How and why does the Internet influence international market growth of the firm’ is justified for investigation. To explore the research question a two-stage approach is used. Firstly, twelve case studies were used to evaluate key concepts, generate hypotheses and to develop a model of Internetalisation for testing. The participants held key positions within their firm, so that rich data could be drawn from international market growth decision makers. Secondly, a quantitative confirmation process analysed the identified themes or constructs, using two hundred and twenty four valid responses. Constructs were evaluated through an exploratory factor analysis, confirmatory factor analysis and structural equation modelling process. Structural equation modelling was used to test the model of =internetalisation‘ to examine the interrelationships between the internationalisation process components: information availability, information usage, interaction communication, international mindset, business relationship usage, psychic distance, the Internet intensity of the firm and international market growth. This study found that the Internet intensity of the firm mediates information availability, information usage, international mindset, and business relationships when firms grow in international markets. Therefore, these results provide empirical evidence that the Internet has a positive influence on international information, knowledge, entrepreneurship and networks and these in turn influence international market growth. The theoretical contributions are three fold. Firstly, the study identifies a holistic model of the impact the Internet has had on the outward internationalisation of the firm. This contribution extends the body of knowledge pertaining to Internet international marketing by mapping and confirming interrelationships between the Internet, internationalisation and growth concepts. Secondly, the study highlights the broad scope and accelerated rate of international market growth of firms. Evidence that the Internet influences the traditional and virtual networks for the pursuit of international market growth extends the current understanding. Thirdly, this study confirms that international information, knowledge, entrepreneurship and network concepts are valid in a single model. Thus, these three contributions identify constructs, measure constructs in a multi-item capacity, map interrelationships and confirm single holistic model of ‗internetalisation‘. The main practical contribution is that the findings identified information, knowledge and entrepreneurial opportunities for firms wishing to maximise international market growth. To capitalise on these opportunities suggestions are offered to assist firms to develop greater Internet intensity and internationalisation capabilities. From a policy perspective, educational institutions and government bodies need to promote more applied programs for Internet international marketing. The study provides future researchers with a platform of identified constructs and interrelationships related to internetalisation, with which to investigate. However, a single study has limitations of generalisability; thus, future research should replicate this study. Such replication or cross validation will assist in the verification of scales used in this research and enhance the validity of causal predications. Furthermore, this study was undertaken in the Australian outward-bound context. Research in other nations, as well as research into inbound internationalisation would be fruitful.

Cascading appearance-based features for visual speaker verification

The cascading appearance-based (CAB) feature extraction technique has established itself as the state of the art in extracting dynamic visual speech features for speech recognition. In this paper, we will focus on investigating the effectiveness of this technique for the related speaker verification application. By investigating the speaker verification ability of each stage of the cascade we will demonstrate that the same steps taken to reduce static speaker and environmental information for the speech recognition application also provide similar improvements for speaker recognition. These results suggest that visual speaker recognition can improve considerable when conducted solely through a consideration of the dynamic speech information rather than the static appearance of the speaker's mouth region.

Mobility and safety are conflicting goals for transport policy makers when making decisions about graduated driver licensing

Policy decisions are frequently influenced by more than research results alone. This review examines one road safety countermeasure, graduated driver licensing, in three jurisdictions and identifies how the conflict between mobility and safety goals can influence policy decisions relating to this countermeasure. Evaluations from around the world of graduated driver licensing have demonstrated clear reductions in crashes for young drivers. However, the introduction of this countermeasure may be affected, both positively and negatively, by the conflict some policy makers experience between ensuring individuals remain both mobile and safe as drivers. This review highlights how this conflict in policy decision making can serve to either facilitate or hinder the introduction of graduated driver licensing systems. However, policy makers whose focus on mobility is too strong when compared with safety may be mistaken, with evidence suggesting that after a graduated driver licensing system is introduced young drivers adapt their behaviour to the new system and remain mobile. As a result, policy makers should consciously acknowledge the conflict between mobility and safety and consider an appropriate balance in order to introduce these systems. Improvements to the licensing system can then be made in an incremental manner as the balance between these two priorities change. Policy makers can achieve an appropriate balance by using empirical evidence as a basis for their decisions.

The speed paradox : the misalignment between driver attitudes and speeding behaviour

This paper reports on a study investigating preferred driving speeds and frequency of speeding of 320 Queensland drivers. Despite growing community concern about speeding and extensive research linking it to road trauma, speeding remains a pervasive, and arguably, socially acceptable behaviour. This presents an apparent paradox regarding the mismatch between beliefs and behaviours, and highlights the necessity to better understand the factors contributing to speeding. Utilising self-reported behaviour and attitudinal measures, results of this study support the notion of a speed paradox. Two thirds of participants agreed that exceeding the limit is not worth the risks nor is it okay to exceed the posted limit. Despite this, more than half (58.4%) of the participants reported a preference to exceed the 100km/hour speed limit, with one third preferring to do so by 10 to 20 km/hour. Further, mean preferred driving speeds on both urban and open roads suggest a perceived enforcement tolerance of 10%, suggesting that posted limits have limited direct influence on speed choice. Factors that significantly predicted the frequency of speeding included: exposure to role models who speed; favourable attitudes to speeding; experiences of punishment avoidance; and the perceived certainty of punishment for speeding. These findings have important policy implications, particularly relating to the use of enforcement tolerances.

Improving automatic speaker verification using SVM techniques

Automatic recognition of people is an active field of research with important forensic and security applications. In these applications, it is not always possible for the subject to be in close proximity to the system. Voice represents a human behavioural trait which can be used to recognise people in such situations. Automatic Speaker Verification (ASV) is the process of verifying a persons identity through the analysis of their speech and enables recognition of a subject at a distance over a telephone channel { wired or wireless. A significant amount of research has focussed on the application of Gaussian mixture model (GMM) techniques to speaker verification systems providing state-of-the-art performance. GMM's are a type of generative classifier trained to model the probability distribution of the features used to represent a speaker. Recently introduced to the field of ASV research is the support vector machine (SVM). An SVM is a discriminative classifier requiring examples from both positive and negative classes to train a speaker model. The SVM is based on margin maximisation whereby a hyperplane attempts to separate classes in a high dimensional space. SVMs applied to the task of speaker verification have shown high potential, particularly when used to complement current GMM-based techniques in hybrid systems. This work aims to improve the performance of ASV systems using novel and innovative SVM-based techniques. Research was divided into three main themes: session variability compensation for SVMs; unsupervised model adaptation; and impostor dataset selection. The first theme investigated the differences between the GMM and SVM domains for the modelling of session variability | an aspect crucial for robust speaker verification. Techniques developed to improve the robustness of GMMbased classification were shown to bring about similar benefits to discriminative SVM classification through their integration in the hybrid GMM mean supervector SVM classifier. Further, the domains for the modelling of session variation were contrasted to find a number of common factors, however, the SVM-domain consistently provided marginally better session variation compensation. Minimal complementary information was found between the techniques due to the similarities in how they achieved their objectives. The second theme saw the proposal of a novel model for the purpose of session variation compensation in ASV systems. Continuous progressive model adaptation attempts to improve speaker models by retraining them after exploiting all encountered test utterances during normal use of the system. The introduction of the weight-based factor analysis model provided significant performance improvements of over 60% in an unsupervised scenario. SVM-based classification was then integrated into the progressive system providing further benefits in performance over the GMM counterpart. Analysis demonstrated that SVMs also hold several beneficial characteristics to the task of unsupervised model adaptation prompting further research in the area. In pursuing the final theme, an innovative background dataset selection technique was developed. This technique selects the most appropriate subset of examples from a large and diverse set of candidate impostor observations for use as the SVM background by exploiting the SVM training process. This selection was performed on a per-observation basis so as to overcome the shortcoming of the traditional heuristic-based approach to dataset selection. Results demonstrate the approach to provide performance improvements over both the use of the complete candidate dataset and the best heuristically-selected dataset whilst being only a fraction of the size. The refined dataset was also shown to generalise well to unseen corpora and be highly applicable to the selection of impostor cohorts required in alternate techniques for speaker verification.

QUT speaker identity verification system for EVALITA 2009

This document outlines the system submitted by the Speech and Audio Research Laboratory at the Queensland University of Technology (QUT) for the Speaker Identity Verication: Application task of EVALITA 2009. This submission consisted of a score-level fusion of three component systems, a joint-factor GMM system and two SVM systems using GLDS and GMM supervector kernels. Development and evaluation results are presented, demonstrating the effectiveness of this fused system approach.

Data-driven background dataset selection for SVM-based speaker verification

The recently proposed data-driven background dataset refinement technique provides a means of selecting an informative background for support vector machine (SVM)-based speaker verification systems. This paper investigates the characteristics of the impostor examples in such highly-informative background datasets. Data-driven dataset refinement individually evaluates the suitability of candidate impostor examples for the SVM background prior to selecting the highest-ranking examples as a refined background dataset. Further, the characteristics of the refined dataset were analysed to investigate the desired traits of an informative SVM background. The most informative examples of the refined dataset were found to consist of large amounts of active speech and distinctive language characteristics. The data-driven refinement technique was shown to filter the set of candidate impostor examples to produce a more disperse representation of the impostor population in the SVM kernel space, thereby reducing the number of redundant and less-informative examples in the background dataset. Furthermore, data-driven refinement was shown to provide performance gains when applied to the difficult task of refining a small candidate dataset that was mis-matched to the evaluation conditions.

Exploiting multiple feature sets in data-driven impostor dataset selection for speaker verification

This study assesses the recently proposed data-driven background dataset refinement technique for speaker verification using alternate SVM feature sets to the GMM supervector features for which it was originally designed. The performance improvements brought about in each trialled SVM configuration demonstrate the versatility of background dataset refinement. This work also extends on the originally proposed technique to exploit support vector coefficients as an impostor suitability metric in the data-driven selection process. Using support vector coefficients improved the performance of the refined datasets in the evaluation of unseen data. Further, attempts are made to exploit the differences in impostor example suitability measures from varying features spaces to provide added robustness.

Driver behaviour and decision making at railway level crossings : An exploratory on-road case study

Crashes at rail level crossings represent a significant problem, both in Australia and worldwide. Advances in driving assessment methods, such as the provision of on-road instrumented test vehicles, now provide researchers with the opportunity to further understand driver behaviour at rail level crossings in ways not previously possible. This paper gives an overview of a recent on-road pilot study of driver behaviour at rail level crossings in which 25 participants drove a pre-determined route, incorporating 4 rail level crossings, using MUARC's instrumented On-Road Test Vehicle (ORTeV). Drivers provided verbal commentary whilst driving the route, and a range of other data were collected, including eye fixations, forward, cockpit and driver video, and vehicle data (speed, braking, steering wheel angle, lane tracking etc). Participants also completed a post trial cognitive task analysis interview. Extracts from the wider analyses are used to examine in depth driver behaviour at one of the rail level crossings encountered during the study. The analysis presented, along with the overall analysis undertaken, gives insight into the driver and wider systems factors that shape behaviour at rail level crossings, and highlights the utility of using a multi-method, instrumented vehicle approach for gathering data regarding driver behaviour in different contexts.