Speaker diarization : "who spoke when"

Speaker diarization is the process of annotating an input audio with information that attributes temporal regions of the audio signal to their respective sources, which may include both speech and non-speech events. For speech regions, the diarization system also specifies the locations of speaker boundaries and assign relative speaker labels to each homogeneous segment of speech. In short, speaker diarization systems effectively answer the question of ‘who spoke when’. There are several important applications for speaker diarization technology, such as facilitating speaker indexing systems to allow users to directly access the relevant segments of interest within a given audio, and assisting with other downstream processes such as summarizing and parsing. When combined with automatic speech recognition (ASR) systems, the metadata extracted from a speaker diarization system can provide complementary information for ASR transcripts including the location of speaker turns and relative speaker segment labels, making the transcripts more readable. Speaker diarization output can also be used to localize the instances of specific speakers to pool data for model adaptation, which in turn boosts transcription accuracies. Speaker diarization therefore plays an important role as a preliminary step in automatic transcription of audio data. The aim of this work is to improve the usefulness and practicality of speaker diarization technology, through the reduction of diarization error rates. In particular, this research is focused on the segmentation and clustering stages within a diarization system. Although particular emphasis is placed on the broadcast news audio domain and systems developed throughout this work are also trained and tested on broadcast news data, the techniques proposed in this dissertation are also applicable to other domains including telephone conversations and meetings audio. Three main research themes were pursued: heuristic rules for speaker segmentation, modelling uncertainty in speaker model estimates, and modelling uncertainty in eigenvoice speaker modelling. The use of heuristic approaches for the speaker segmentation task was first investigated, with emphasis placed on minimizing missed boundary detections. A set of heuristic rules was proposed, to govern the detection and heuristic selection of candidate speaker segment boundaries. A second pass, using the same heuristic algorithm with a smaller window, was also proposed with the aim of improving detection of boundaries around short speaker segments. Compared to single threshold based methods, the proposed heuristic approach was shown to provide improved segmentation performance, leading to a reduction in the overall diarization error rate. Methods to model the uncertainty in speaker model estimates were developed, to address the difficulties associated with making segmentation and clustering decisions with limited data in the speaker segments. The Bayes factor, derived specifically for multivariate Gaussian speaker modelling, was introduced to account for the uncertainty of the speaker model estimates. The use of the Bayes factor also enabled the incorporation of prior information regarding the audio to aid segmentation and clustering decisions. The idea of modelling uncertainty in speaker model estimates was also extended to the eigenvoice speaker modelling framework for the speaker clustering task. Building on the application of Bayesian approaches to the speaker diarization problem, the proposed approach takes into account the uncertainty associated with the explicit estimation of the speaker factors. The proposed decision criteria, based on Bayesian theory, was shown to generally outperform their non- Bayesian counterparts.

Building Healthy Communities : GP Network, Medicare Local and Primary Health Care in the Wheatbelt Region of Western Australia

• Government reports consistently recognise the importance of Primary Health Care to an efficient health system. Barriers identified in Australia’s Primary Health Care include workforce pressures, increase rate of chronic disease, and equitable access to Primary Health Care services. • General Practitioners (GPs) are the key to the successful delivery of Primary Health Care especially in rural and remote regions such as the Wheatbelt region in Western Australia (WA). • The Wheatbelt region of WA is vast: some 72,500 residents spread across 150,000km2 in 43 Local Government Authorities catchments. Majority of the Wheatbelt residents live in small towns. There is a higher reported rates of chronic disease, more at risk of chronic diseases and less utilisation of Primary Health Care services in this region. • General practice patients in the Wheatbelt are among those most in need of Primary Health Care services. • Wheatbelt GP Network (the “Network”) was established in 1998. It is a key health service delivery stakeholder in the Wheatbelt. • The Network has responded to the health needs of the community by creating a mobile Allied Health Team that works closely with GPs and is adaptive to ensure priority needs are met. • The Medicare Local model introduced by the Australian Government in 2011 aimed to improve the delivery of Primary Health Care services by improved health planning and coordinating service delivery. • Little if any recognition has been given to the outstanding work that many Divisions of General Practice have done in improving the delivery of Primary Health Care services such as the Network. • The Network has continued to support GPs and general practices and created a complementary system that integrated general practice with the work of an Allied Health Team. Its program mix is extensive. • The Network has consistently delivered on-required contract outputs and has a fifteen (15) years history of operating successfully in a large geographical area comprising in the main smaller communities that cannot support the traditional health services model. • The complexity of supporting International Medical Graduates in the region requires special attention. • The introduction of the Medicare Local in the South West of WA and their intention to take over the delivery of health services, thus effectively shutting the Network will have catastrophic consequences and cannot be supported economically. • The Network proposes to create a new model, built on its past work that increases the delivery of Primary Health Care services through its current Allied Health Team. • The proposal uses the Wheatbelt GP Super Clinic currently under construction in Northam, part of the Network and funded by the Australian Government is a key to the proposed new model. • Wheatbelt GP Super Clinic is different from existing models of GP Super Clinics around Australia which focus predominately on co-location of services. Wheatbelt GP Super Clinic utilises a hub and spoke model of service outreach to small rural towns to ensure equitable Primary Health Care coverage and continuum of care in a financially responsible and viable manner. In particular, the Wheatbelt GP Super Clinic recognises the importance of Allied Health Professionals and will involve them in a collaborative model with rural general practice. • The proposed model advocated by the Network aims to substitute the South West WA Medicare Local direct service delivery proposed for the Wheatbelt. The Network’s proposed model is to expand on the current hub and spoke model of Primary Health Care delivery to otherwise small unviable Wheatbelt towns. A flexible and adaptive skill mix of Allied Health Professionals, Nurse Practitioners and GPs ensure equitable access to service. Expanded scope of practices are utilised to reduce duplication of service and concentration of services in major towns. This involves a partnership approach. • If the proposed model not funded, the Network and the Wheatbelt region will stand to lose 16 Allied Health Professionals and defeats the purpose of Australian Government current funding for the construction of the Wheatbelt GP Super Clinic. • The Network has considered how its model can best be funded. It proposes a re-allocation of funds made available to the South West WA Medicare Local. • This submission argues that the proposal for the South West WA Medicare Local to take over the service delivery of Primary Health Care services in the Wheatbelt makes no economic sense when an existing agency (the Network) has the infrastructure in place, is experienced in working in this geographical area that has special needs and is capable to expand its programs to meet demand.

Exploring pedestrian accessibility and walkability : insight from public place observations in inner-urban higher density Brisbane, Australia

As planners work to create more sustainable and liveable urban environments, a priority is to transition away from prioritising the automobile and towards enhancing the pedestrian experience. Thus, this research explores the experience of pedestrian accessibility in inner-urban higher-density Brisbane in Australia, drawing on findings from semi-structured in-depth interviews with 24 residents and over 100 hours of public place observations in three case-study neighbourhoods. The interviews took place in residents homes and explored their experience of higher density living and their neighbourhood, whilst observations were recorded through a combination of methods including photographs, sketch maps, recordings and field journals. Observation locations included retail and commercial space, roads, parkland and open space, with multiple observations at each location. A thematic analysis identified common themes in both interviews and the observations, with this paper focusing on residents’ lived experience in urban built environments. This analysis revealed that pedestrian accessibility is linked to access to local amenities and direct routes, aesthetics, sense of community, ownership of space and safety. In particular, observations revealed how pedestrian accessibility and route-taking works with, against or in spite of the design features of urban environments, as well as the importance of the social use of the built environment. Residents spoke about although walking quick and preferred for local amenities, the decision to walk was moderated by factors such as time of day and perceived safety. Measures to ensure and improve the pedestrian accessibility of urban areas needs to take into account the propensity for people to prefer and improvise direct routes (often to the detriment of traffic safety considerations), the importance of ongoing maintenance and upgrading of walking infrastructure and the importance of aesthetically pleasing and safe walking environments. By combining interviews and observations, this research highlights the current dominance of the automobile culture in Brisbane and the layers of meaning, experiences and complexity hidden within the pedestrian experience.

How do customers of a financial services institution judge its communications

Communications are important for relationships within a marketing channel from both a theoretical and managerial perspective. Yet it is a problematic area for scholars. Thus, this research addresses the problem of how do customers of a financial services institution perceive communications with an ideal institution? This study's case research methodology used in-depth interviews with 34 carefully selected customers of a building society. The factors that make up customers' attitudes about corporate communications for an ideal financial services institution were identified and actual perceptions were compared against that ideal. The findings confirmed the importance of communications for customers in a relationship with a financial services provider and suggested communication priorities for customers in this context. In addition, the findings suggested sources of communication dissatisfaction for customers. These findings build upon the literature that speculates about customer perceptions of communications with organizations but provides little evidence to support hypotheses. The contributions arose from the emphasis on the customers' own attitudes and the patterns found within them.

Raman spectroscopic characteristics of phthalocyanine and naphthalocyanine in sandwich-type phthalocyaninato and porphyrinato rare earth complexes Part 5. – Raman spectroscopic characteristics of naphthalocyanine in mixed [tetrakis(4-tert-butylphenyl)porphyrinato]-(naphthalocyaninato) rare earth double-deckers

Raman spectra were recorded in the range 400–1800 cm−1 for a series of 15 mixed \[tetrakis(4-tert-butylphenyl)porphyrinato](2,3-naphthalocyaninato) rare earth double-deckers M(TBPP)(Nc) (M = Y; La–Lu except Pm) using laser excitation at 632.8 and 785 nm. Comparisons with bis(naphthalocyaninato) rare earth counterparts reveal that the vibrations of the metallonaphthalocyanine M(Nc) fragment dominate the Raman features of M(TBPP)(Nc). When excited with radiation of 632.8 nm, the most intense vibration appears at about 1595 cm−1, due to the naphthalene stretching. These complexes exhibit the marker Raman band for Nc•− as a medium-intense band in the range 1496–1507 cm−1, attributed to the coupling of pyrrole and aza stretching, while the marker Raman band of Nc2− in intermediate-valence Ce(TBPP)(Nc) appears as a strong band at 1493 cm−1 and is due to the isoindole stretchings. By contrast, when excited with radiation of 785 nm that is in close resonance with the main Q absorption band of the naphthalocyanine ligand, the ring radial vibrations at ca 680 and 735 cm−1 for MIII(TBPP)(Nc) are selectively intensified and are the most intense bands. For the cerium double-decker, the most intense vibration also acting as the marker Raman band of Nc2− appears at 1497 cm−1 with contributions from both pyrrole CC and aza CN stretches. The same vibrational modes show weak to medium intensity scattering at 1506–1509 cm−1 for MIII(TBPP)(Nc) and this is the marker Raman band of Nc•− when thus excited. The scatterings due to the Nc breathings, ring radial vibration, aza group stretchings, naphthalene stretchings, benzoisoindole stretchings and the coupling of pyrrole CC and aza CN stretchings in MIII(TBPP)(Nc) are all slightly blue shifted along with the decrease in rare earth ionic radius, confirming the effects of increased ring–ring interactions on the Raman characteristics of naphthalocyanine in the mixed ring double-deckers.

Work/Family Balance: HRM Policy and Practice in Australia

An employee's inability to balance work and family responsibilities has resulted in an increase in stress related illnesses. Historically, research into the nexus between work and family has primarily focused on the work/family conflict relationship, predominately investigating the impact of this conflict on parents, usually mothers. To date research has not sufficiently examined the human resource management practices that enable all parents to achieve a balance between their work and family lives. This paper explores the relationship between contemporary family friendly HRM policies and employed parents perceptions of work/family enhancement, work/family satisfaction, propensity to turnover, and work/family conflict. Self-report questionnaire data from 326 men and women is analysed and discussed to enable organisations to consider the use of family friendly policies and thus create a convergence between the well-being of employees and the effectiveness of the organisation.

Diesel bus emissions of submicrometer particles measured in a tunnel study

The emission factors of a bus fleet consisting of approximately three hundreds diesel powered buses were measured in a tunnel study under well controlled conditions during a two-day monitoring campaign in Brisbane. The number concentration of particles in the size range 0.017-0.7 m was monitored simultaneously by two Scanning Mobility Particle Sizers located at the tunnel’s entrance and exit. The mean value of the number emission factors was found to be (2.44±1.41)×1014 particles km-1. The results are in good agreement with the emission factors determined from steady-state dynamometer testing of 12 buses from the same Brisbane City bus fleet, thus indicating that when carefully designed, both approaches, the dynamometer and on-road studies, can provide comparable results, applicable for the assessment of the effect of traffic emissions on airborne particle pollution.

Extending conceptual models for Web based applications

The next phase envisioned for the World Wide Web is automated ad-hoc interaction between intelligent agents, web services, databases and semantic web enabled applications. Although at present this appears to be a distant objective, there are practical steps that can be taken to advance the vision. We propose an extension to classical conceptual models to allow the definition of application components in terms of public standards and explicit semantics, thus building into web-based applications, the foundation for shared understanding and interoperability. The use of external definitions and the need to store outsourced type information internally, brings to light the issue of object identity in a global environment, where object instances may be identified by multiple externally controlled identification schemes. We illustrate how traditional conceptual models may be augmented to recognise and deal with multiple identities.

Collaboration and Engagement Throughout The Supply Chain : The Role of Government

Collaboration is acknowledged as a key to continued growth in the Australian construction industry. Government, as a major industry client, has an important role to play with respect to fostering collaboration and ensuring the global competitiveness of the industry. The paper draws upon data collected for the Construction 2020 study and aims to demonstrate that government can a) help to break down the adversarial situation that currently exists between clients, project managers and subcontractors; and b) allow the supply chain to collaborate more effectively in terms of satisfying the relational and financial needs of all parties. Government can also provide a clear set of guidelines (backed up by a functional dispute resolution system) that will promote confidence with respect to forging relationships. Thus, the paper will discuss the way in which public policy can be more closely aligned with actual industry needs in order to promote greater collaboration.

GPX - Gardens Point XML Information Retrieval at INEX 2004

Traditional information retrieval (IR) systems respond to user queries with ranked lists of relevant documents. The separation of content and structure in XML documents allows individual XML elements to be selected in isolation. Thus, users expect XML-IR systems to return highly relevant results that are more precise than entire documents. In this paper we describe the implementation of a search engine for XML document collections. The system is keyword based and is built upon an XML inverted file system. We describe the approach that was adopted to meet the requirements of Content Only (CO) and Vague Content and Structure (VCAS) queries in INEX 2004.

The ZMET Technique: A New Paradigm for Improving Marketing and Marketing Research

For decades, marketing and marketing research have been based on a concept of consumer behaviour that is deeply embedded in a linear notion of marketing activities. With increasing regularity, key organising frameworks for marketing and marketing activities are being challenged by academics and practitioners alike. In turn, this has led to the search for new approaches and tools that will help marketers understand the interaction among attitudes, emotions and product/brand choice. More recently, the approach developed by Harvard Professor, Gerald Zaltman, referred to as the Zaltman Metaphor Elicitation Technique (ZMET) has gained considerable interest. This paper seeks to demonstrate the effectiveness of this alternative qualitative method, using a non-conventional approach, thus providing a useful contribution to the qualitative research area.

Adaptive optical flow for person tracking

Person tracking systems are dependent on being able to locate a person accurately across a series of frames. Optical flow can be used to segment a moving object from a scene, provided the expected velocity of the moving object is known; but successful detection also relies on being able segment the background. A problem with existing optical flow techniques is that they don’t discriminate the foreground from the background, and so often detect motion (and thus the object) in the background. To overcome this problem, we propose a new optical flow technique, that is based upon an adaptive background segmentation technique, which only determines optical flow in regions of motion. This technique has been developed with a view to being used in surveillance systems, and our testing shows that for this application it is more effective than other standard optical flow techniques.

A maintenance-data-model of enterprise resource planning

Two distinct maintenance-data-models are studied: a government Enterprise Resource Planning (ERP) maintenance-data-model, and the Software Engineering Industries (SEI) maintenance-data-model. The objective is to: (i) determine whether the SEI maintenance-data-model is sufficient in the context of ERP (by comparing with an ERP case), (ii) identify whether the ERP maintenance-data-model in this study has adequately captured the essential and common maintenance attributes (by comparing with the SEI), and (iii) proposed a new ERP maintenance-data-model as necessary. Our findings suggest that: (i) there are variations to the SEI model in an ERP-context, and (ii) there are rooms for improvements in our ERP case’s maintenance-data-model. Thus, a new ERP maintenance-data-model capturing the fundamental ERP maintenance attributes is proposed. This model is imperative for: (i) enhancing the reporting and visibility of maintenance activities, (ii) monitoring of the maintenance problems, resolutions and performance, and (iii) helping maintenance manager to better manage maintenance activities and make well-informed maintenance decisions.

Fundamental sounds

Fundamental Sounds was a live, intercultural and multidisciplinary concert that presented a new synthesis of music, performance & visual arts addressing the imperative of sustainability in a new and evocative form. The outcome was a ninety-minute concert, performed at a major concert hall venue, involving four live musicians, numerous performers & large-scale projections. The images and the concert were scripted in three key phases that spoke to three epochs of human evolution identified by ontological designer and futurist Tony Fry - ‘Pre-Settlement’, ‘Settlement’ and the era that he suggests that we have now entered – ‘Unsettlement’ (in mind body and spirit). The entire work was professionally recorded for presentation on DVD and audio CD.----- Fundamental Sounds achieved a new synthesis between quality performance forms and cogent critical ideas, engendering an increasingly reflective position for audiences around today’s “era of unsettlement” – an epoch Fry has recognized that we must now move to quickly displace through adopting fundamentally sustainable modes of being and becoming.----- The concert was well attended and evoked a range of strong, reflective reactions from its audiences who were also invited to join and participate within a subsequent ‘community of change’ initiated at that time.

Clipping noise compensation for OFDMA systems

This paper presents an efficient low-complexity clipping noise compensation scheme for PAR reduced orthogonal frequency division multiple access (OFDMA) systems. Conventional clipping noise compensation schemes proposed for OFDM systems are decision directed schemes which use demodulated data symbols. Thus these schemes fail to deliver expected performance in OFDMA systems where multiple users share a single OFDM symbol and a specific user may only know his/her own modulation scheme. The proposed clipping noise estimation and compensation scheme does not require the knowledge of the demodulated symbols of the other users, making it very promising for OFDMA systems. It uses the equalized output and the reserved tones to reconstruct the signal by compensating the clipping noise. Simulation results show that the proposed scheme can significantly improve the system performance.