Acoustic keyword spotting in speech with applications to data mining

Keyword Spotting is the task of detecting keywords of interest within continu- ous speech. The applications of this technology range from call centre dialogue systems to covert speech surveillance devices. Keyword spotting is particularly well suited to data mining tasks such as real-time keyword monitoring and unre- stricted vocabulary audio document indexing. However, to date, many keyword spotting approaches have su®ered from poor detection rates, high false alarm rates, or slow execution times, thus reducing their commercial viability. This work investigates the application of keyword spotting to data mining tasks. The thesis makes a number of major contributions to the ¯eld of keyword spotting. The ¯rst major contribution is the development of a novel keyword veri¯cation method named Cohort Word Veri¯cation. This method combines high level lin- guistic information with cohort-based veri¯cation techniques to obtain dramatic improvements in veri¯cation performance, in particular for the problematic short duration target word class. The second major contribution is the development of a novel audio document indexing technique named Dynamic Match Lattice Spotting. This technique aug- ments lattice-based audio indexing principles with dynamic sequence matching techniques to provide robustness to erroneous lattice realisations. The resulting algorithm obtains signi¯cant improvement in detection rate over lattice-based audio document indexing while still maintaining extremely fast search speeds. The third major contribution is the study of multiple veri¯er fusion for the task of keyword veri¯cation. The reported experiments demonstrate that substantial improvements in veri¯cation performance can be obtained through the fusion of multiple keyword veri¯ers. The research focuses on combinations of speech background model based veri¯ers and cohort word veri¯ers. The ¯nal major contribution is a comprehensive study of the e®ects of limited training data for keyword spotting. This study is performed with consideration as to how these e®ects impact the immediate development and deployment of speech technologies for non-English languages.

Lift@Weimar : sustainable interaction with food, technology, and the city (Workshop)

This workshop explores innovative approaches to understanding and cultivating sustainable food culture in urban environments via human-computer-interaction (HCI) design and ubiquitous technologies. We perceive the city as an intersecting network of people, place, and technology in constant transformation. Our 2009 OZCHI workshop, Hungry 24/7? HCI Design for Sustainable Food Culture, opened a new space for discussion on this intersection amongst researchers and practitioners from diverse backgrounds including academia, government, industry, and non-for-profit organisations. Building on the past success, this new instalment of the workshop series takes a more refined view on mobile human-food interaction and the role of interactive media in engaging citizens to cultivate more sustainable everyday human-food interactions on the go. Interactive media in this sense is distributed, pervasive, and embedded in the city as a network. The workshop addresses environmental, health, and social domains of sustainability by bringing together insights across disciplines to discuss conceptual and design approaches in orchestrating mobility and interaction of people and food in the city as a network of people, place, technology, and food.

Strategising knowledge-based urban development : knowledge city transformations of Brisbane, Australia

In the global knowledge economy, knowledge-intensive industries and knowledge workers are extensively seen as the primary factors to improve the welfare and competitiveness of cities. To attract and retain such industries and workers, cities produce knowledge-based urban development strategies, and therefore such strategising has become an important development mechanism for cities and their economies. The paper discusses the critical connections between knowledge city foundations and integrated knowledge-based urban development mechanisms in both the local and regional level. In particular, the paper investigates Brisbane’s knowledge-based urban development strategies that support gentrification, attraction, and retention of investment and talent. Furthermore, the paper develops a knowledge-based urban development assessment framework to provide a clearer understanding of the local and regional policy frameworks, and relevant applications of Brisbane’s knowledge-based urban development experience, in becoming a prosperous knowledge city. The paper, with its knowledge-based urban development assessment framework, scrutinises Brisbane’s four development domains in detail: economy; society; institutional; built and natural environments. As part of the discussion of the case study findings, the paper describes the global orientation of Brisbane within the frame of regional and local level knowledge-based urban development strategies performing well. Although several good practices from Brisbane have already been internationally acknowledged, the research reveals that Brisbane is still in the early stages of its knowledge-based urban development implementation. Consequently, the development of a monitoring system for all knowledge-based urban development at all levels is highly crucial in accurately measuring the success and failure of specific knowledge-based urban development policies, and Brisbane’s progress towards a knowledge city transformation.

Beyond statistical procedures for predictive modelling: Data mining algorithms and support for university research at QUT

In a seminal data mining article, Leo Breiman [1] argued that to develop effective predictive classification and regression models, we need to move away from the sole dependency on statistical algorithms and embrace a wider toolkit of modeling algorithms that include data mining procedures. Nevertheless, many researchers still rely solely on statistical procedures when undertaking data modeling tasks; the sole reliance on these procedures has lead to the development of irrelevant theory and questionable research conclusions ([1], p.199). We will outline initiatives that the HPC & Research Support group is undertaking to engage researchers with data mining tools and techniques; including a new range of seminars, workshops, and one-on-one consultations covering data mining algorithms, the relationship between data mining and the research cycle, and limitations and problems with these new algorithms. Organisational limitations and restrictions to these initiatives are also discussed.

An evaluation methodology for the tangible and intangible assets of city-regions : the 6K1C framework

Together with hard and soft networks tangible and intangible regional assets play an important role in the knowledge-based development of competing city-regions. The aim of this paper, therefore, is to investigate the best ways of managing invaluable tangible and intangible assets of city-regions. The paper explores the importance of asset management of city-regions by giving special emphasis on their knowledge asset base. This paper develops and introduces a theoretical framework to conceptualise a new approach to articulate the strategic planning mechanism, so called the 6K1C framework. The 6K1C framework is part of the strategic planning process of continuous improvement of overall public sector performance. The framework provides a proactive check-list approach integrated for managing and harnessing tangible and intangible assets of the post-industrial city-regions.

Minimising transport disadvantage to support knowledge city formation : applying the capability approach to select indicators

Purpose–The aims of this paper are to demonstrate the application of Sen’s theory of well-being, the capability approach; to conceptualise the state of transportation disadvantage; and to underpin a theoretical sounds indicator selection process. Design/methodology/approach–This paper reviews and examines various measurement approaches of transportation disadvantage in order to select indicators and develop an innovative framework of urban transportation disadvantage. Originality/value–The paper provides further understanding of the state of transportation disadvantage from the capability approach perspective. In addition, building from this understanding, a validated and systematic framework is developed to select relevant indicators. Practical implications –The multi-indicator approach has a high tendency to double count for transportation disadvantage, increase the number of TDA population and only accounts each indicator for its individual effects. Instead, indicators that are identified based on a transportation disadvantage scenario will yield more accurate results. Keywords – transport disadvantage, the capability approach, accessibility, measuring urban transportation disadvantage, indicators selection Paper type – Academic Research Paper

Transnational business masculinities : media representations of gender and management in global mining corporations

This paper examines Australian media representations of the male managers of two global mining corporations, Rio Tinto and BHP Billiton. These organizations are transnational (or multinational) corporations with assets and/or operations across national boundaries (Dunning and Lundan, 2008), and indeed their respective Chief Executive Officers, Tom Albanese and Marius Kloppers are two of the most economically (and arguably politically) powerful in the world overseeing 37 000 and 39 000 employees internationally. With a 2008 profit of US$15.962 billion and assets of US$ 75.889 Billion BHP Billiton is the world's largest mining company. In terms of its profits and assets Rio Tinto ranks fourth in the world, but with operations in six countries (mainly Canada and Australia) and a 2008 profit of US$10.3 billion it is also emblematic of the transnational in that its ‘budget is larger than that of all but a few nations’ (Giddens, 2003, p. 62).

Transforming people, place, and technology : towards re-creative city

This session is titled TRANSFORM! Opportunities and Challenges of Digital Content for Creative Economy. Some of the key concepts for this session include: 1. City / Economy 2. Creativity 3. Digital content 4. Transformation All of us would agree that these terms describe pertinent characteristics of contemporary world, the epithet of which is the ‘network era.’ I was thinking about what I would like to discuss here and what you, leading experts in divergent fields, would be interested to hear about. As the keynote for this session and as one of the first speakers for the entire conference, I see my role as an initiator for imagination, the wilder the better, posing questions rather than answers. Also given the session title Transform!, I wish to change this slightly to Transforming People, Place, and Technology: Towards Re-­creative City in an attempt to take us away a little from the usual image depicted by the given topic. Instead, I intend to sketch a more holistic picture by reflecting on and extrapolating the four key concepts from the urban informatics point of view. To do so, I use ‘city’ as the primary guiding concept for my talk rather than probably more expected ‘digital media’ or ‘creative economy.’ You may wonder what I mean by re-­creative city. I will explain this in time by looking at the key concepts from these four respective angles: 1. Living city 2. Creative city 3. Re-­‐creative city 4. Opportunities and Challenges to arrive at a speculative yet probable image of the city that we may aspire to transform our current cities into. First let us start by considering the ‘living city.’

Community-based public health: an Online Decision Support Systems : for Logan city, Australia

Introduction Among the many requirements of establishing community health, a healthy urban environment stands out as significant one. A healthy urban environment constantly changes and improves community well-being and expands community resources. The promotion efforts for such an environment, therefore, must include the creation of structures and processes that actively work to dismantle existing community inequalities. In general, these processes are hard to manage; therefore, they require reliable planning and decision support systems. Current and previous practices justify that the use of decision support systems in planning for healthy communities have significant impacts on the communities. These impacts include but are not limited to: increasing collaboration between stakeholders and the general public; improving the accuracy and quality of the decision making process; enhancing healthcare services; and improving data and information availability for health decision makers and service planners. Considering the above stated reasons, this study investigates the challenges and opportunities of planning for healthy communities with the specific aim of examining the effectiveness of participatory planning and decision systems in supporting the planning for such communities. Methods This study introduces a recently developed methodology, which is based on an online participatory decision support system. This new decision support system contributes to solve environmental and community health problems, and to plan for healthy communities. The system also provides a powerful and effective platform for stakeholders and interested members of the community to establish an empowered society and a transparent and participatory decision making environment. Results The paper discusses the preliminary findings from the literature review of this decision support system in a case study of Logan City, Queensland. Conclusion The paper concludes with future research directions and applicability of this decision support system in health service planning elsewhere.

Developing a competitive city through healthy decision-making

This chapter investigates the challenges and opportunities associated with planning for a competitive city. The chapter is based on the assumption that a healthy city is a fundamental prerequisite for a competitive city. Thus, it is critical to examine the local determinants of health and factor these into any planning efforts. The main focus of the chapter is on the role of e-health planning, by utilising web-based geographic decision support systems. The proposed novel decision support system would provide a powerful and effective platform for stakeholders to access essential data for decision-making purposes. The chapter also highlights the need for a comprehensive information framework to guide the process of planning for healthy cities. Additionally, it discusses the prospects and constraints of such an approach. In summary, this chapter outlines the potential insights of using information science-based framework and suggests practical planning methods, as part of a broader e-health approach for improving the health characteristics of competitive cities.

A Two-stage information filtering based on rough decision rule and pattern mining

Information Overload and Mismatch are two fundamental problems affecting the effectiveness of information filtering systems. Even though both term-based and patternbased approaches have been proposed to address the problems of overload and mismatch, neither of these approaches alone can provide a satisfactory solution to address these problems. This paper presents a novel two-stage information filtering model which combines the merits of term-based and pattern-based approaches to effectively filter sheer volume of information. In particular, the first filtering stage is supported by a novel rough analysis model which efficiently removes a large number of irrelevant documents, thereby addressing the overload problem. The second filtering stage is empowered by a semantically rich pattern taxonomy mining model which effectively fetches incoming documents according to the specific information needs of a user, thereby addressing the mismatch problem. The experimental results based on the RCV1 corpus show that the proposed twostage filtering model significantly outperforms the both termbased and pattern-based information filtering models.

Creative industry and world city construction : Beijing as a creative world city

The study of the creative industries is not much more than a decade old. What makes it fascinating is that it is dealing with a rapidly evolving process, where a good deal of Schumpeterian ‘creative destruction’ – of old industries, business models, and some familiar cultural and creative pursuits – can already be observed. What happens next – and who will be the winner – is hard to predict. Furthermore, the creative industries encompass both large-scale ‘industry’ (media, publishing, digital applications) and individual creative talent; both economic and cultural values, and both global reach and local context. Thus, the challenge is to integrate ‘top-down’ policy and planning with ‘bottom-up’ experimentation and innovation. There is always the promise that this new creative ecology will provide some novel answers to problems of wealth-creation for emergent economies, new solutions to problems of intellectual emancipation for individuals, and sustainable development for that most intense incubator of creative ideas, the city.

An intelligent data mining technique for product quality improvement

Advances in data mining have provided techniques for automatically discovering underlying knowledge and extracting useful information from large volumes of data. Data mining offers tools for quick discovery of relationships, patterns and knowledge in large complex databases. Application of data mining to manufacturing is relatively limited mainly because of complexity of manufacturing data. Growing self organizing map (GSOM) algorithm has been proven to be an efficient algorithm to analyze unsupervised DNA data. However, it produced unsatisfactory clustering when used on some large manufacturing data. In this paper a data mining methodology has been proposed using a GSOM tool which was developed using a modified GSOM algorithm. The proposed method is used to generate clusters for good and faulty products from a manufacturing dataset. The clustering quality (CQ) measure proposed in the paper is used to evaluate the performance of the cluster maps. The paper also proposed an automatic identification of variables to find the most probable causative factor(s) that discriminate between good and faulty product by quickly examining the historical manufacturing data. The proposed method offers the manufacturers to smoothen the production flow and improve the quality of the products. Simulation results on small and large manufacturing data show the effectiveness of the proposed method.