Elicitation techniques for the evaluation of speech under stress: Towards a framework for use in a controlled environment

Existing work in Computer Science and Electronic Engineering demonstrates that Digital Signal Processing techniques can effectively identify the presence of stress in the speech signal. These techniques use datasets containing real or actual stress samples i.e. real-life stress such as 911 calls and so on. Studies that use simulated or laboratory-induced stress have been less successful and inconsistent. Pervasive, ubiquitous computing is increasingly moving towards voice-activated and voice-controlled systems and devices. Speech recognition and speaker identification algorithms will have to improve and take emotional speech into account. Modelling the influence of stress on speech and voice is of interest to researchers from many different disciplines including security, telecommunications, psychology, speech science, forensics and Human Computer Interaction (HCI). The aim of this work is to assess the impact of moderate stress on the speech signal. In order to do this, a dataset of laboratory-induced stress is required. While attempting to build this dataset it became apparent that reliably inducing measurable stress in a controlled environment, when speech is a requirement, is a challenging task. This work focuses on the use of a variety of stressors to elicit a stress response during tasks that involve speech content. Biosignal analysis (commercial Brain Computer Interfaces, eye tracking and skin resistance) is used to verify and quantify the stress response, if any. This thesis explains the basis of the author’s hypotheses on the elicitation of affectively-toned speech and presents the results of several studies carried out throughout the PhD research period. These results show that the elicitation of stress, particularly the induction of affectively-toned speech, is not a simple matter and that many modulating factors influence the stress response process. A model is proposed to reflect the author’s hypothesis on the emotional response pathways relating to the elicitation of stress with a required speech content. Finally the author provides guidelines and recommendations for future research on speech under stress. Further research paths are identified and a roadmap for future research in this area is defined.

Treatment trials for neonatal seizures: the effect of design on sample size

Neonatal seizures are common in the neonatal intensive care unit. Clinicians treat these seizures with several anti-epileptic drugs (AEDs) to reduce seizures in a neonate. Current AEDs exhibit sub-optimal efficacy and several randomized control trials (RCT) of novel AEDs are planned. The aim of this study was to measure the influence of trial design on the required sample size of a RCT. We used seizure time courses from 41 term neonates with hypoxic ischaemic encephalopathy to build seizure treatment trial simulations. We used five outcome measures, three AED protocols, eight treatment delays from seizure onset (Td) and four levels of trial AED efficacy to simulate different RCTs. We performed power calculations for each RCT design and analysed the resultant sample size. We also assessed the rate of false positives, or placebo effect, in typical uncontrolled studies. We found that the false positive rate ranged from 5 to 85% of patients depending on RCT design. For controlled trials, the choice of outcome measure had the largest effect on sample size with median differences of 30.7 fold (IQR: 13.7–40.0) across a range of AED protocols, Td and trial AED efficacy (p<0.001). RCTs that compared the trial AED with positive controls required sample sizes with a median fold increase of 3.2 (IQR: 1.9–11.9; p<0.001). Delays in AED administration from seizure onset also increased the required sample size 2.1 fold (IQR: 1.7–2.9; p<0.001). Subgroup analysis showed that RCTs in neonates treated with hypothermia required a median fold increase in sample size of 2.6 (IQR: 2.4–3.0) compared to trials in normothermic neonates (p<0.001). These results show that RCT design has a profound influence on the required sample size. Trials that use a control group, appropriate outcome measure, and control for differences in Td between groups in analysis will be valid and minimise sample size.

Peanut Allergen Threshold Study (PATS): validation of eliciting doses using a novel single-dose challenge protocol

Background: The eliciting dose (ED) for a peanut allergic reaction in 5% of the peanut allergic population, the ED05, is 1.5 mg of peanut protein. This ED05 was derived from oral food challenges (OFC) that use graded, incremental doses administered at fixed time intervals. Individual patients’ threshold doses were used to generate population dose-distribution curves using probability distributions from which the ED05 was then determined. It is important to clinically validate that this dose is predictive of the allergenic response in a further unselected group of peanut-allergic individuals. Methods/Aims: This is a multi-centre study involving three national level referral and teaching centres. (Cork University Hospital, Ireland, Royal Children’s Hospital Melbourne, Australia and Massachusetts General Hospital, Boston, U.S.A.) The study is now in process and will continue to run until all centres have recruited 125 participates in each respective centre. A total of 375 participants, aged 1–18 years will be recruited during routine Allergy appointments in the centres. The aim is to assess the precision of the predicted ED05 using a single dose (6 mg peanut = 1.5 mg of peanut protein) in the form of a cookie. Validated Food Allergy related Quality of Life Questionnaires-(FAQLQ) will be self-administered prior to OFC and 1 month after challenge to assess the impact of a single dose OFC on FAQL. Serological and cell based in vitro studies will be performed. Conclusion: The validation of the ED05 threshold for allergic reactions in peanut allergic subjects has potential value for public health measures. The single dose OFC, based upon the statistical dose-distribution analysis of past challenge trials, promises an efficient approach to identify the most highly sensitive patients within any given food-allergic population.

Acoustic behaviour, ecology and social structure of bottlenose dolphins (Tursiops truncatus, Montagu 1821) in the North Atlantic

Communication is important for social and other behavioural interactions in most marine mammal species. The bottlenose dolphin (Tursiops truncatus, Montagu, 1821) is a highly social species that use whistles as communication calls to express identity and to initiate and maintain contact between socially interactive individuals. In this thesis, the degree of variability in whistle behaviour and whistle characteristics was examined between different habitats on a range of spatial scales. The whistle characteristics that best discriminated between different communities were investigated, along with exploration of whistle variation in relation to habitat type, levels of social interaction and relatedness. Finally, the use and variability of individually distinctive calls (signature whistles) within and between Irish and US waters were also examined. Relatively high levels of whistle variation were found within a genetically and socially isolated population of dolphins in the Shannon Estuary, reflecting the need for individual identification and distinctive whistles in a population with long term site fidelity and high levels of social cohesion. Variation between reproductively separate communities in Irish waters was relatively small except between animals in inshore compared with continental shelf waters. The greatest differences in whistle structure overall were evident between dolphins using inshore and offshore US waters, likely reflecting social isolation of the two distinct ecotypes that occur in these waters but also variation in behaviour or habitat conditions. Variation found among inshore communities in US waters reflected similarities in habitat use and levels of social interaction. These findings suggest that vocal variation is socially mediated, behaviourally maintained and dependent on levels of social contact between individuals. The findings contribute to our understanding of the interaction of factors influencing vocalisation behaviour in this behaviourally complex and ecologically plastic species.

Reasoning with imprecise trade-offs in decision making under certainty and uncertainty

In many real world situations, we make decisions in the presence of multiple, often conflicting and non-commensurate objectives. The process of optimizing systematically and simultaneously over a set of objective functions is known as multi-objective optimization. In multi-objective optimization, we have a (possibly exponentially large) set of decisions and each decision has a set of alternatives. Each alternative depends on the state of the world, and is evaluated with respect to a number of criteria. In this thesis, we consider the decision making problems in two scenarios. In the first scenario, the current state of the world, under which the decisions are to be made, is known in advance. In the second scenario, the current state of the world is unknown at the time of making decisions. For decision making under certainty, we consider the framework of multiobjective constraint optimization and focus on extending the algorithms to solve these models to the case where there are additional trade-offs. We focus especially on branch-and-bound algorithms that use a mini-buckets algorithm for generating the upper bound at each node of the search tree (in the context of maximizing values of objectives). Since the size of the guiding upper bound sets can become very large during the search, we introduce efficient methods for reducing these sets, yet still maintaining the upper bound property. We define a formalism for imprecise trade-offs, which allows the decision maker during the elicitation stage, to specify a preference for one multi-objective utility vector over another, and use such preferences to infer other preferences. The induced preference relation then is used to eliminate the dominated utility vectors during the computation. For testing the dominance between multi-objective utility vectors, we present three different approaches. The first is based on a linear programming approach, the second is by use of distance-based algorithm (which uses a measure of the distance between a point and a convex cone); the third approach makes use of a matrix multiplication, which results in much faster dominance checks with respect to the preference relation induced by the trade-offs. Furthermore, we show that our trade-offs approach, which is based on a preference inference technique, can also be given an alternative semantics based on the well known Multi-Attribute Utility Theory. Our comprehensive experimental results on common multi-objective constraint optimization benchmarks demonstrate that the proposed enhancements allow the algorithms to scale up to much larger problems than before. For decision making problems under uncertainty, we describe multi-objective influence diagrams, based on a set of p objectives, where utility values are vectors in Rp, and are typically only partially ordered. These can be solved by a variable elimination algorithm, leading to a set of maximal values of expected utility. If the Pareto ordering is used this set can often be prohibitively large. We consider approximate representations of the Pareto set based on ϵ-coverings, allowing much larger problems to be solved. In addition, we define a method for incorporating user trade-offs, which also greatly improves the efficiency.

The human papillomavirus and cancer: a multiphase study investigating preventative behaviours in young males

Background: The Human Papillomavirus (HPV) is one of the world’s most common sexually transmitted infections, and a causative factor of oropharyngeal, anal and penile cancers in males. Worldwide, an estimated 39,000 HPV-associated cancers occur each year in men. The highest rates of HPV infection are found in adults aged 18 to 28 years. Clinical evidence indicates that use of a condom in addition to obtaining the HPV vaccine provides the greatest protection from HPV infections. Aim: To explore young men’s attitudes, beliefs, and behavioural intention in relation to receiving the HPV vaccine and using a condom correctly and consistently. Collectively, both behaviours are linked to the prevention of HPV transmission and associated infections with HPV. Method: A multi- phase study, underpinned by the Theory of Planned Behaviour, involving a qualitative belief elicitation, pilot, and quantitative cross-sectional study was conducted. A belief elicitation (n=12) phase was used to generate items to include in a newly developed research instrument. Post pilot the research instrument was utilised in a cross sectional online survey to explore the attitudes, beliefs, and behavioural intention of young men (n= 359) with regard to receiving the HPV vaccine, and using a condom correctly and consistently. Data Collection: Data collection took place over a three month time frame. Male participants were recruited from a university in Southern Ireland via a student email system, as well as posting advertisements on numerous health, social and sports websites. Sample: Three hundred and fifty nine male participants aged 18- 28 years completed the online questionnaire. Data Analysis: Data were analysed using SPSS. Descriptive, correlational, multiple and hierarchical regression analysis were performed on the indirect and direct variables of the Theory of Planned Behaviour i.e. attitude, subjective norm, perceived behavioural control, and intention. Status variables were also included in descriptive analysis and hierarchical regressions. Findings are presented through text and graphical representation. Results: Alarming sexual health statistics identified that only 44.3% of participants always used a condom, and 78.6% never used a condom for oral sex. Furthermore, findings reveal that the constructs of the Theory of Planned Behaviour adequately measure male’s attitudes, beliefs and behavioural intention with regard to both behaviours. The Theory of Planned Behaviour has assisted in identifying how social pressures play an influential role in relation to males receiving the HPV vaccine. Attitudes presented as the most significant predictor of male’s intentions to use a condom correctly and consistently. Intention to perform both behaviours was identified as moderate to high. Conclusion: This study has contributed to the field of HPV research, as it is the first piece of research to explore preventative HPV behaviours i.e. receiving the HPV vaccine, and condom use, amongst young males, utilising the Theory of Planned Behaviour. A deeper understanding of young male’s attitudes, beliefs, and behavioural intention on this topic has been achieved. Additionally, a new robust research instrument has been constructed. Findings from this study will undoubtedly help in the implementation of the HPV vaccine in Ireland, as well as influence health promotion campaigns aimed at young males, addressing the topic of condom use.

ALD: adaptive layer distribution for scalable video

Recent years have witnessed a rapid growth in the demand for streaming video over the Internet and mobile networks, exposes challenges in coping with heterogeneous devices and varying network throughput. Adaptive schemes, such as scalable video coding, are an attractive solution but fare badly in the presence of packet losses. Techniques that use description-based streaming models, such as multiple description coding (MDC), are more suitable for lossy networks, and can mitigate the effects of packet loss by increasing the error resilience of the encoded stream, but with an increased transmission byte cost. In this paper, we present our adaptive scalable streaming technique adaptive layer distribution (ALD). ALD is a novel scalable media delivery technique that optimises the tradeoff between streaming bandwidth and error resiliency. ALD is based on the principle of layer distribution, in which the critical stream data are spread amongst all packets, thus lessening the impact on quality due to network losses. Additionally, ALD provides a parameterised mechanism for dynamic adaptation of the resiliency of the scalable video. The Subjective testing results illustrate that our techniques and models were able to provide levels of consistent high-quality viewing, with lower transmission cost, relative to MDC, irrespective of clip type. This highlights the benefits of selective packetisation in addition to intuitive encoding and transmission.