Likelihood-maximising frameworks for enhanced in-car speech recognition

Speech recognition in car environments has been identified as a valuable means for reducing driver distraction when operating non-critical in-car systems. Likelihood-maximising (LIMA) frameworks optimise speech enhancement algorithms based on recognised state sequences rather than traditional signal-level criteria such as maximising signal-to-noise ratio. Previously presented LIMA frameworks require calibration utterances to generate optimised enhancement parameters which are used for all subsequent utterances. Sub-optimal recognition performance occurs in noise conditions which are significantly different from that present during the calibration session - a serious problem in rapidly changing noise environments. We propose a dialog-based design which allows regular optimisation iterations in order to track the changing noise conditions. Experiments using Mel-filterbank spectral subtraction are performed to determine the optimisation requirements for vehicular environments and show that minimal optimisation assists real-time operation with improved speech recognition accuracy. It is also shown that the proposed design is able to provide improved recognition performance over frameworks incorporating a calibration session.

Purity evaluation and influence of carbon nanotube on carbon nanotube/graphite thermal stability

High resolution thermogravimetry has been used to evaluate the carbonaceous content in a commercial sample of single-walled carbon nanotube (SWNT). The content of SWNTs in the sample was found to be at least 77mass% which was supported by images obtained with scanning and transmission electron microscopies (SEM and TEM). Furthermore, the influence of SWNT addition on the thermal stability of graphite in mixtures of SWNT/graphite at different proportions was investigated. The graphite stability decreased with the increased of SWNT content in the overall range of composition. This behavior could be due to the close contact between these carbonaceous species as determined by SEM analysis.

Perceptions of aging across 26 cultures and their culture-level associates

College students (N = 3,435) in 26 cultures reported their perceptions of age-related changes in physical, cognitive, and socioemotional areas of functioning and rated societal views of aging within their culture. There was widespread cross-cultural consensus regarding the expected direction of aging trajectories with (1) perceived declines in societal views of aging, physical attractiveness, the ability to perform everyday tasks, and new learning, (2) perceived increases in wisdom, knowledge, and received respect, and (3) perceived stability in family authority and life satisfaction. Cross-cultural variations in aging perceptions were associated with culture-level indicators of population aging, education levels, values, and national character stereotypes. These associations were stronger for societal views on aging and perceptions of socioemotional changes than for perceptions of physical and cognitive changes. A consideration of culture-level variables also suggested that previously reported differences in aging perceptions between Asian and Western countries may be related to differences in population structure.

Robust speech recognition using speech enhancement

Automatic Speech Recognition (ASR) has matured into a technology which is becoming more common in our everyday lives, and is emerging as a necessity to minimise driver distraction when operating in-car systems such as navigation and infotainment. In “noise-free” environments, word recognition performance of these systems has been shown to approach 100%, however this performance degrades rapidly as the level of background noise is increased. Speech enhancement is a popular method for making ASR systems more ro- bust. Single-channel spectral subtraction was originally designed to improve hu- man speech intelligibility and many attempts have been made to optimise this algorithm in terms of signal-based metrics such as maximised Signal-to-Noise Ratio (SNR) or minimised speech distortion. Such metrics are used to assess en- hancement performance for intelligibility not speech recognition, therefore mak- ing them sub-optimal ASR applications. This research investigates two methods for closely coupling subtractive-type enhancement algorithms with ASR: (a) a computationally-efficient Mel-filterbank noise subtraction technique based on likelihood-maximisation (LIMA), and (b) in- troducing phase spectrum information to enable spectral subtraction in the com- plex frequency domain. Likelihood-maximisation uses gradient-descent to optimise parameters of the enhancement algorithm to best fit the acoustic speech model given a word se- quence known a priori. Whilst this technique is shown to improve the ASR word accuracy performance, it is also identified to be particularly sensitive to non-noise mismatches between the training and testing data. Phase information has long been ignored in spectral subtraction as it is deemed to have little effect on human intelligibility. In this work it is shown that phase information is important in obtaining highly accurate estimates of clean speech magnitudes which are typically used in ASR feature extraction. Phase Estimation via Delay Projection is proposed based on the stationarity of sinusoidal signals, and demonstrates the potential to produce improvements in ASR word accuracy in a wide range of SNR. Throughout the dissertation, consideration is given to practical implemen- tation in vehicular environments which resulted in two novel contributions – a LIMA framework which takes advantage of the grounding procedure common to speech dialogue systems, and a resource-saving formulation of frequency-domain spectral subtraction for realisation in field-programmable gate array hardware. The techniques proposed in this dissertation were evaluated using the Aus- tralian English In-Car Speech Corpus which was collected as part of this work. This database is the first of its kind within Australia and captures real in-car speech of 50 native Australian speakers in seven driving conditions common to Australian environments.

Home depot in Chile: case study

Retailing is rapidly becoming a global industry and many retailers are expanding to foreign markets. However, several retailers successful in their home countries have failed in emerging markets such as Chile. Little is known why these retailers succeed in some venues and not others. A case study of the failed operations of Home Depot in that Chilean market was developed in order to understand this issue in more depth. This case study included an analysis of the Chilean marketplace, expert and consumer interviews, and analysis of data from secondary sources. Finding showed difference in that institutional environment between Chile and the U.S., due to a higher family and relational orientation in Chile. Home Depot defied institutional pressures and maintained standardized retail practices.

Collaborative business process modeling using 3D virtual environments

Process modeling is a complex organizational task that requires many iterations and communication between the business analysts and the domain specialists involved in the process modeling. The challenge of process modeling is exacerbated, when the process of modeling has to be performed in a cross-organizational, distributed environment. Some systems have been developed to support collaborative process modeling, all of which use traditional 2D interfaces. We present an environment for collaborative process modeling, using 3D virtual environment technology. We make use of avatar instantiations of user ego centres, to allow for the spatial embodiment of the user with reference to the process model. We describe an innovative prototype collaborative process modeling approach, implemented as a modeling environment in Second Life. This approach leverages the use of virtual environments to provide user context for editing and collaborative exercises. We present a positive preliminary report on a case study, in which a test group modelled a business process using the system in Second Life.

Enablers and barriers to the organizational adoption of sustainable business practices

Individuals, organizations, and governments are increasingly becoming aware of the necessity of sustainability in living, organizing, performing, and managing work. In this context, “green IS” has become an established colloquial term, acknowledging that information technology, corporate information systems, and the surrounding practices are both a contributor to the sustainability challenge and a potential enabler for green and sustainable practices. To date, however, there are few reported studies on the role of information systems for the challenge, and solution, of sustainability. This paper presents results from a case study of a world-wide operating IT software solution provider that is engaged in the development and adoption of sustainable practices. Our study suggests that the adoption of sustainable practices comes along with a number of particularities. We found information technology to be a key enabler of transparency about the progress of sustainability operations. We further found personal, motivator factors as well as organizational factors such as business inclusion, strategy definition, and a dialectic top-management and bottom-up support, to play a role in enabling a company to manage their sustainability. We describe a set of conjectures forthcoming from our case analysis, and detail some implications for further research in this area.

An Integrative framework of the factors affecting process model understanding : a learning perspective

Process models are used by information professionals to convey semantics about the business operations in a real world domain intended to be supported by an information system. The understandability of these models is vital to them actually being used. After all, what is not understood cannot be acted upon. Yet until now, understandability has primarily been defined as an intrinsic quality of the models themselves. Moreover, those studies that looked at understandability from a user perspective have mainly conceptualized users through rather arbitrary sets of variables. In this paper we advance an integrative framework to understand the role of the user in the process of understanding process models. Building on cognitive psychology, goal-setting theory and multimedia learning theory, we identify three stages of learning required to realize model understanding, these being Presage, Process, and Product. We define eight relevant user characteristics in the Presage stage of learning, three knowledge construction variables in the Process stage and three potential learning outcomes in the Product stage. To illustrate the benefits of the framework, we review existing process modeling work to identify where our framework can complement and extend existing studies.

How relationships can be utilized for service bundling

The phenomenon of organizations offering service bundles can typically be observed in dynamic markets with heterogeneous customer demand. Available literature broaching the issue of service bundling covers strategic considerations for organizations related to their respective market position as well as their pricing options for different bundle configurations. However, little guidance can be found regarding the identification of potential bundle candidates and the actual process of bundling. In this paper, we present an approach to service bundling that can be utilized by organizations to identify services that are suitable for bundling. The contribution of the paper is twofold. Firstly, the proposed method represents a structured conceptualization approach for organizations to facilitate the creation of bundles in practice based on empirical findings. Secondly, from a Design Science research perspective, the proposed method represents an innovative artifact that extends the academic knowledge base related to service management.

Enterprise systems in universities : a teaching case

This teaching case aims to contribute to understanding the phenomenon of Enterprise Systems (ES) implementations in universities. Through this case, students will gain understanding of the importance of ‘contextual elements’ for large scale information systems (IS) implementations, in particular ES. This teaching case illustrates how these contextual factors contribute to the success or failure of such implementations, and how they can influence the decisions that dictate the lifecycle of such systems. The case describes ES implementations at a leading Australian university, and presents a rich account of the institutional, national and industry-sector contexts that have influenced the directions and decisions taken. The journey encountered with the main Enterprise Systems that support Financials, Human Resources and Facilities are described suggesting the lifecycle phases, critical success factors and lessons learnt.

Service identification through value chain analysis and prioritization

In a resource constrained business world, strategic choices must be made on process improvement and service delivery. There are calls for more agile forms of enterprises and much effort is being directed at moving organizations from a complex landscape of disparate application systems to that of an integrated and flexible enterprise accessing complex systems landscapes through service oriented architecture (SOA). This paper describes the deconstruction of an enterprise into business services using value chain analysis as each element in the value chain can be rendered as a business service in the SOA. These business services are explicitly linked to the attainment of specific organizational strategies and their contribution to the attainment of strategy is assessed and recorded. This contribution is then used to provide a rank order of business service to strategy. This information facilitates executive decision making on which business service to develop into the SOA. The paper describes an application of this Critical Service Identification Methodology (CSIM) to a case study.

The effect of dialect mismatch on likelihood-maximising speech enhancement for noise-robust speech recognition

Traditional speech enhancement methods optimise signal-level criteria such as signal-to-noise ratio, but these approaches are sub-optimal for noise-robust speech recognition. Likelihood-maximising (LIMA) frameworks are an alternative that optimise parameters of enhancement algorithms based on state sequences generated for utterances with known transcriptions. Previous reports of LIMA frameworks have shown significant promise for improving speech recognition accuracies under additive background noise for a range of speech enhancement techniques. In this paper we discuss the drawbacks of the LIMA approach when multiple layers of acoustic mismatch are present – namely background noise and speaker accent. Experimentation using LIMA-based Mel-filterbank noise subtraction on American and Australian English in-car speech databases supports this discussion, demonstrating that inferior speech recognition performance occurs when a second layer of mismatch is seen during evaluation.

The application of phonetic distribution normalisation to likelihood-maximising speech enhancement for robust ASR

Traditional speech enhancement methods optimise signal-level criteria such as signal-to-noise ratio, but such approaches are sub-optimal for noise-robust speech recognition. Likelihood-maximising (LIMA) frameworks on the other hand, optimise the parameters of speech enhancement algorithms based on state sequences generated by a speech recogniser for utterances of known transcriptions. Previous applications of LIMA frameworks have generated a set of global enhancement parameters for all model states without taking in account the distribution of model occurrence, making optimisation susceptible to favouring frequently occurring models, in particular silence. In this paper, we demonstrate the existence of highly disproportionate phonetic distributions on two corpora with distinct speech tasks, and propose to normalise the influence of each phone based on a priori occurrence probabilities. Likelihood analysis and speech recognition experiments verify this approach for improving ASR performance in noisy environments.

Integrating qualitative and quantitative approaches in cross-cultural research

The affects associated with culture, the values inherent in cultures and the identification of cultural assumptions are popular topics in recent management and Information Systems (IS) research. The main focus in relevant IS research over the years, has been on the comparison of cultural artifacts in different cultural settings. Despite these studies we need to ask whether there is a general approach to how culture can be researched in a rigorous manner? What are the issues that arise in cross- cultural research that have a bearing on decisions about a suitable research approach? What are the most appropriate methodologies to be used in cross-cultural research? Which is more appropriate, a qualitative, a quantitative or a mixed- method research approach? This paper will discuss important considerations in the process of deciding on the best research approach for cross-cultural projects. A case study will be then be reported as an example revealing the merits of integrating qualitative and quantitative approaches followed by a thorough discussion on the issues which may arise during this process.

The validity and structure of culture-level personality scores: Data from ratings of young adolescents

We examined properties of culture-level personality traits in ratings of targets (N=5,109) ages 12 to 17 in 24 cultures. Aggregate scores were generalizable across gender, age, and relationship groups and showed convergence with culture-level scores from previous studies of self-reports and observer ratings of adults, but they were unrelated to national character stereotypes. Trait profiles also showed cross-study agreement within most cultures, 8 of which had not previously been studied. Multidimensional scaling showed that Western and non-Western cultures clustered along a dimension related to Extraversion. A culture-level factor analysis replicated earlier findings of a broad Extraversion factor but generally resembled the factor structure found in individuals. Continued analysis of aggregate personality scores is warranted.