Automatic speaker recognition under adverse conditions

Speaker verification is the process of verifying the identity of a person by analysing their speech. There are several important applications for automatic speaker verification (ASV) technology including suspect identification, tracking terrorists and detecting a person’s presence at a remote location in the surveillance domain, as well as person authentication for phone banking and credit card transactions in the private sector. Telephones and telephony networks provide a natural medium for these applications. The aim of this work is to improve the usefulness of ASV technology for practical applications in the presence of adverse conditions. In a telephony environment, background noise, handset mismatch, channel distortions, room acoustics and restrictions on the available testing and training data are common sources of errors for ASV systems. Two research themes were pursued to overcome these adverse conditions: Modelling mismatch and modelling uncertainty. To directly address the performance degradation incurred through mismatched conditions it was proposed to directly model this mismatch. Feature mapping was evaluated for combating handset mismatch and was extended through the use of a blind clustering algorithm to remove the need for accurate handset labels for the training data. Mismatch modelling was then generalised by explicitly modelling the session conditions as a constrained offset of the speaker model means. This session variability modelling approach enabled the modelling of arbitrary sources of mismatch, including handset type, and halved the error rates in many cases. Methods to model the uncertainty in speaker model estimates and verification scores were developed to address the difficulties of limited training and testing data. The Bayes factor was introduced to account for the uncertainty of the speaker model estimates in testing by applying Bayesian theory to the verification criterion, with improved performance in matched conditions. Modelling the uncertainty in the verification score itself met with significant success. Estimating a confidence interval for the "true" verification score enabled an order of magnitude reduction in the average quantity of speech required to make a confident verification decision based on a threshold. The confidence measures developed in this work may also have significant applications for forensic speaker verification tasks.

Mobile phones in PNG villages : an island village experience

As a new communication technology expands in a disadvantaged, rural area of a developing country, changes take place in the lives of the people in the area. The paper examines the introduction of mobile telephony into a rural village in Papua New Guinea, and contains findings from field research conducted in February 2009. The analysis is undertaken through a social lens, providing an understanding of the roles of mobile phones in this community by foregrounding the feelings, thoughts and attitudes expressed by the village people. This in turn enables a deeper understanding of the sociological effects related to the uptake of mobile telephony.

Tsunami alert : the difference a phone makes

As a new communication technology expands in a disadvantaged, rural area of a developing country, this process of change can radically affect the quality and volume of available information. Substantial growth has occurred in the telecommunication sector in Papua New Guinea (PNG) in the last three years. Mobile telephony is rapidly rolling out to rural and remote localities, following decades of inadequate service provision. The paper examines the introduction of mobile telephones into a rural village in PNG, and focuses on an example of changed information access afforded by the mobile telephone, through comparing the village’s experience of two tsunami alerts: one immediately prior to the introduction of mobile phone services in the area, and the other two years after mobile phone reception became available. The research demonstrates a key application of newly introduced information and communication technologies - to benefit disadvantaged, rural communities in emergency situations.

Review of de Bruijn, M., F. Nyamnjoh and I. Brinkman (eds.). 2009. Mobile phones : the new talking drums of everyday Africa

Since the late 1990s, there has been great enthusiasm expressed about the positive impact that can be obtained for poor and disadvantaged people from information and communication technologies (ICTs). This school of thought among researchers and practitioners is identified as ICTs for development (ICT4D). By contrast, a growing number of researchers eschew the technologically deterministic nature of the claims being made for development progress and seek to understand the role of technology in people’s lives, primarily through ethnographic studies. This book, which focuses on mobile telephony on the African continent, fits into the latter body of literature, with several authors explicitly stating they are examining social and cultural settings and are not taking a technologically deterministic view. The book captures the diverse ways various communities are using this communication technology. It adds to the burgeoning field of mobile phone studies, in which an increasing number of studies is emerging from developing countries.

Towards a service framework for remote sales support via augmented reality

Real-time sales assistant service is a problematic component of remote delivery of sales support for customers. Solutions involving web pages, telephony and video support prove problematic when seeking to remotely guide customers in their sales processes, especially with transactions revolving around physically complex artefacts. This process involves a number of services that are often complex in nature, ranging from physical compatibility and configuration factors, to availability and credit services. We propose the application of a combination of virtual worlds and augmented reality to create synthetic environments suitable for remote sales of physical artefacts, right in the home of the purchaser. A high level description of the service structure involved is shown, along with a use case involving the sale of electronic goods and services within an example augmented reality application. We expect this work to have application in many sales domains involving physical objects needing to be sold over the Internet.

The mobile phone : the new communication drum of Papua New Guinea

This thesis examines the role of mobile telephony in rural communities in Papua New Guinea (PNG). It is a threshold study which reports on research conducted in the earliest stages of mobile phone adoption in these areas. It explores the ways in which this new technology changes people’s lives, social structures and relationships. The research focuses on non-urban communities, which previously had little or no access to modern communication technologies, but which are in some cases still using traditional forms of communication such as drums. It has found that the introduction of mobile telecommunications has generally been viewed positively, although several negative concerns have been strongly felt. Specific benefits related to enhanced communication with relatives and friends living away from home villages, and use of the technology in time-critical emergencies or crises. Difficulties have arisen with respect to the cost of owning and operating a handset, as well as financial and logistical challenges when recharging handset batteries, particularly in areas with no mains electricity supply. Perceived damaging effects of mobile phone access related to sex, crime and pornography. The changes taking place are described through a social lens, by foregrounding the perceptions of villagers. The perspectives of key informants, such as telecommunication company managers, are also discussed. Employing the technique of triangulation (using different methods and sources) has helped to validate the findings of the research project. The sources constantly overlap and agree on the main themes, such as those outlined above. PNG is a developing country which performs poorly on a wide range of development indicators. A large majority of the people live outside of the major towns and cities. It is therefore worthwhile investigating the introduction of mobile phone technology in rural areas. These areas often have poor access to services, including transport, health, education and banking. Until 2007, communities in such regions fell outside of mobile phone coverage areas. In the case of all ten villages discussed in this thesis, there has never been any landline telephone infrastructure available. Therefore, this research on mobile phones is in effect documenting the first ever access to any kind of phone in these communities. This research makes a unique contribution to knowledge about the role of communication in PNG, and has implications for policy, practice and theory. In the policy arena, the thesis aids understanding of the impact which communication sector competition and regulation can have on rural and relatively isolated communities. There are three practical problems which have emerged from the research: cost, battery recharging difficulties and breakage are all major obstacles to uptake and use of mobile telephony in rural communities. Efforts to reduce usage costs, enable easier recharging, and design more robust handsets would allow for increased utilisation of mobile phones for a range of purposes. With respect to the realm of theory, this research sits amongst the most recent scholarship in the mobile phone field, located within the broader communication theory area. It recommends cautionary reading of any literature which suggests that mobile phones will reduce poverty and increase incomes in poor, rural communities in developing countries. Nonetheless, the present research adds weight to mobile phone studies which suggest that the primary advantages of mobile phones in such settings are for the satisfactions of communication of itself, and for social interaction among loved ones.

Interactive product browsing and configuration using remote augmented reality sales services

Real-time remote sales assistance is an underdeveloped component of online sales services. Solutions involving web page text chat, telephony and video support prove problematic when seeking to remotely guide customers in their sales processes, especially with configurations of physically complex artefacts. Recently, there has been great interest in the application of virtual worlds and augmented reality to create synthetic environments for remote sales of physical artefacts. However, there is a lack of analysis and development of appropriate software services to support these processes. We extend our previous work with the detailed design of configuration context services to support the management of an interactive sales session using augmented reality. We detail the context and configuration services required, presenting a novel data service streaming configuration information to the vendor for business analytics. We expect that a fully implemented configuration management service, based on our design, will improve the remote sales experience for both customers and vendors alike via analysis of the streamed information.

Writing and publishing research articles in teams

This paper provides insight into writing scholarly research articles by working collaboratively in teams. Collaborative writing is increasingly common practice within organizational and university contexts. While there is a growing volume of literature which examines various aspects of collaborative writing from challenges to politics, less attention is paid to practical aspects of how to write in teams, particularly within the context of research training. The article examines practical approaches to collaborative writing, and delineates primary continuities and disjunctions between ‘traditional collaboration’ relying largely upon physical face-to-face meetings, and ‘virtual teams’ which are geographically or organizationally dispersed and communicate via virtual, mobile, online or telephony enabled communication.

Tsunami alert : the mobile phone difference

Substantial growth has occurred in the telecommunication sector in Papua New Guinea (PNG) since 2007. Mobile telephony has spread to rural and remote localities, following decades of inadequate telephone services. This paper examines the introduction of mobile telephones into a rural village in PNG, and focuses on information access during emergency situations. It considers three tsunami alerts: one immediately prior to the introduction of mobile phone services in the area, and two which occurred after mobile phone reception became available. The research shows that for people with limited access to information, responses to threats such as tsunamis can be inappropriate and driven by fear and panic. By contrast, when there is reliable, timely information available, measured responses can be adopted. This research demonstrates how the use of newly-introduced communication technologies for handling emergencies may work in practice, benefitting people in poorer, rural communities.

Kerberos based security system for session initiation protocol

Session Initiation Protocol (SIP) is developed to provide advanced voice services over IP networks. SIP unites telephony and data world, permitting telephone calls to be transmitted over Intranets and Internet. Increase in network performance and new mechanisms for guaranteed quality of service encourage this consolidation to provide toll cost savings. Security comes up as one of the most important issues when voice communication and critical voice applications are considered. Not only the security methods provided by traditional telephony systems, but also additional methods are required to overcome security risks introduced by the public IP networks. SIP considers security problems of such a consolidation and provides a security framework. There are several security methods defined within SIP specifications and extensions. But, suggested methods can not solve all the security problems of SIP systems with various system requirements. In this thesis, a Kerberos based solution is proposed for SIP security problems, including SIP authentication and privacy. The proposed solution tries to establish flexible and scalable SIP system that will provide desired level of security for voice communications and critical telephony applications.

AR Services Video

Video presented as part of the USECA 2011 workshop at WISE 2011. Real-time sales assistant service is a problematic component of remote delivery of sales support for customers. Solutions involving web pages, telephony and video support prove problematic when seeking to remotely guide customers in their sales processes, especially with transactions revolving around physically complex artefacts. This process involves a number of services that are often complex in nature, ranging from physical compatibility and configuration factors, to availability and credit services. We propose the application of a combination of virtual worlds and augmented reality to create synthetic environments suitable for remote sales of physical artefacts, right in the home of the purchaser. A high level description of the service structure involved is shown, along with a use case involving the sale of electronic goods and services within an example augmented reality application. We expect this work to have application in many sales domains involving physical objects needing to be sold over the Internet.

YAWL4Industry : reflections on using YAWL for industry projects

The Yet Another Workflow Language (YAWL) language and environment has been used to prototype, verify, execute and analyse business processes in a wide variety of industrial domains, such as telephony, construction, supply chain, insurance services, medical environments, personnel management and the creative arts. These engagements offer the YAWL researcher community a great opportunity to validate our research findings within an industry setting, as well as discovery of possible enhancements from the end user perspective. This paper describes three such industry projects, discusses why YAWL was chosen and how it was used in each, and reacts on the insights gained along the way.

Longing band play at beautiful hope

This article enquires into the contextual dimensions of Indonesian consumerism by presenting the rise to national fame of provincial boy band, Kangen (Longing) Band. The case of Kangen Band suggests that Indonesian consumerism entails new ways of heralding the masses that rely on and play with old generic terms, kampungan (hick-ish) and ‘Melayu’ (Malay). It also reveals some of the specificities of the Indonesian consumerist environment, in which ring back tones, pirate recordings and corporatized fandom are important resources in the formation of consumer subjectivities.

Design of a TDD Multisector TDM MAC for the WiFiRe Proposal for Rural Broadband Access

The WiFiRe (WiFi Rural Extension) proposal for rural broadband access is being developed under the aegis of CEWIT. The system leverages the widely available, and highly cost-reduced, WiFi chipsets. However, only the physical layer from these chipsets is retained. A single base station carries several WiFi transceivers, each serving one sector of the cell, and all operating on the same WiFi channel in a time division duplex (TDD) manner. We replace the contention based WiFi MAC with a single-channel TDD multisector TDM MAC similar to the WiMax MAC. In this paper we discuss in detail the issues in designing such a MAC for the purpose of carrying packet voice telephony and for Internet access. The problem of determining the optimal spatial reuse is formulated and the optimal spatial reuse and the corresponding cell size is derived. Then the voice and data scheduler is designed. It is shown how throughput fairness can be implemented in the data scheduler. A capacity assessment of the system is also provided.