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.

Diversity of accuracy profiles for absolute pitch recognition

Most advanced musicians are able to identify and label a heard pitch if given an opportunity to compare it to a known reference note. This is called ‘relative pitch’ (RP). A much rarer skill is the ability to identify and label a heard pitch without the need for a reference. This is colloquially referred to as ‘perfect pitch’, but appears in the academic literature as ‘absolute pitch’ (AP). AP is considered by many as a remarkable skill. As people do not seem able to develop it intentionally, it is generally regarded as innate. It is often seen as a unitary skill and that a set of identifiable criteria can distinguish those who possess the skill from those who do not. However, few studies have interrogated these notions. The present study developed and applied an interactive computer program to map pitch-labelling responses to various tonal stimuli without a known reference tone available to participants. This approach enabled the identification of the elements of sound that impacted on AP. Pitch-labelling responses of 14 participants with AP were recorded for their accuracy. Each participant’s response to the stimuli was unique. Their accuracy of labelling varied across dimensions such as timbre, range and tonality. The diversity of performance between individuals appeared to reflect their personal musical experience histories.

STRATÉGÉ – Study of Transparent Recognition, Accreditation Tools and Experience in a Global Environment

Engineering graduates of today, face a working environment that assumes global mobility in the labour market. This challenge means, amongst universities worldwide, a demand to increase the globalisation of educational programs, context, and increase and support the mobility of students through mechanisms such as student exchange and double masters degrees. Engineering student mobility from Australia is low with only a few Engineering Faculties encouraging students to go internationally. This comparative study, using universities in Australia and Europe, of feedback from students who have been on exchange or proposing to go on exchange, employers and faculty addresses the motivators and barriers to student mobility and exchange from the perspectives of the university, faculty, students and employers. Recommendations will be presented on how student mobility and exchange can be improved, and mechanisms such as double Masters Degrees, dual accreditation and Erasmus Mundus 2009 – 2013 can be utilised to improve student mobility.

How environmental and organizational complexity affects opportunity recognition in development projects

New product development projects are experiencing increasing internal and external project complexity. Complexity leadership theory proposes that external complexity requires adaptive and enabling leadership, which facilitates opportunity recognition (OR). We ask whether internal complexity also requires OR for increased adaptability. We extend a model of EO and OR to conclude that internal complexity may require more careful OR. This means that leaders of technically or structurally complex projects need to evaluate opportunities more carefully than those in projects with external or technological complexity.

Constraints on the complete optimization of human motion

In sport and exercise biomechanics, forward dynamics analyses or simulations have frequently been used in attempts to establish optimal techniques for performance of a wide range of motor activities. However, the accuracy and validity of these simulations is largely dependent on the complexity of the mathematical model used to represent the neuromusculoskeletal system. It could be argued that complex mathematical models are superior to simple mathematical models as they enable basic mechanical insights to be made and individual-specific optimal movement solutions to be identified. Contrary to some claims in the literature, however, we suggest that it is currently not possible to identify the complete optimal solution for a given motor activity. For a complete optimization of human motion, dynamical systems theory implies that mathematical models must incorporate a much wider range of organismic, environmental and task constraints. These ideas encapsulate why sports medicine specialists need to adopt more individualized clinical assessment procedures in interpreting why performers' movement patterns may differ.

Selecting, optimizing and fusing ‘salient’ Gabor features for facial expression recognition

This paper describes a novel framework for facial expression recognition from still images by selecting, optimizing and fusing ‘salient’ Gabor feature layers to recognize six universal facial expressions using the K nearest neighbor classifier. The recognition comparisons with all layer approach using JAFFE and Cohn-Kanade (CK) databases confirm that using ‘salient’ Gabor feature layers with optimized sizes can achieve better recognition performance and dramatically reduce computational time. Moreover, comparisons with the state of the art performances demonstrate the effectiveness of our approach.

Library technician course recognition : meeting the challenge of a distributed national education program

This paper looks at the challenges presented for the Australian Library and Information Association by its role as the professional association responsible for ensuring the quality of Australian library technician graduates. There is a particular focus on the issue of course recognition, where the Association's role is complicated by the need to work alongside the national quality assurance processes that have been established by the relevant technical education authorities. The paper describes the history of course recognition in Australia; examines the relationship between course recognition and other quality measures; and describes the process the Association has undertaken recently to ensure appropriate professional scrutiny in a changing environment of accountability.

Improved detection and tracking of objects in surveillance video

Surveillance networks are typically monitored by a few people, viewing several monitors displaying the camera feeds. It is then very difficult for a human operator to effectively detect events as they happen. Recently, computer vision research has begun to address ways to automatically process some of this data, to assist human operators. Object tracking, event recognition, crowd analysis and human identification at a distance are being pursued as a means to aid human operators and improve the security of areas such as transport hubs. The task of object tracking is key to the effective use of more advanced technologies. To recognize an event people and objects must be tracked. Tracking also enhances the performance of tasks such as crowd analysis or human identification. Before an object can be tracked, it must be detected. Motion segmentation techniques, widely employed in tracking systems, produce a binary image in which objects can be located. However, these techniques are prone to errors caused by shadows and lighting changes. Detection routines often fail, either due to erroneous motion caused by noise and lighting effects, or due to the detection routines being unable to split occluded regions into their component objects. Particle filters can be used as a self contained tracking system, and make it unnecessary for the task of detection to be carried out separately except for an initial (often manual) detection to initialise the filter. Particle filters use one or more extracted features to evaluate the likelihood of an object existing at a given point each frame. Such systems however do not easily allow for multiple objects to be tracked robustly, and do not explicitly maintain the identity of tracked objects. This dissertation investigates improvements to the performance of object tracking algorithms through improved motion segmentation and the use of a particle filter. A novel hybrid motion segmentation / optical flow algorithm, capable of simultaneously extracting multiple layers of foreground and optical flow in surveillance video frames is proposed. The algorithm is shown to perform well in the presence of adverse lighting conditions, and the optical flow is capable of extracting a moving object. The proposed algorithm is integrated within a tracking system and evaluated using the ETISEO (Evaluation du Traitement et de lInterpretation de Sequences vidEO - Evaluation for video understanding) database, and significant improvement in detection and tracking performance is demonstrated when compared to a baseline system. A Scalable Condensation Filter (SCF), a particle filter designed to work within an existing tracking system, is also developed. The creation and deletion of modes and maintenance of identity is handled by the underlying tracking system; and the tracking system is able to benefit from the improved performance in uncertain conditions arising from occlusion and noise provided by a particle filter. The system is evaluated using the ETISEO database. The dissertation then investigates fusion schemes for multi-spectral tracking systems. Four fusion schemes for combining a thermal and visual colour modality are evaluated using the OTCBVS (Object Tracking and Classification in and Beyond the Visible Spectrum) database. It is shown that a middle fusion scheme yields the best results and demonstrates a significant improvement in performance when compared to a system using either mode individually. Findings from the thesis contribute to improve the performance of semi-automated video processing and therefore improve security in areas under surveillance.

Scatter difference NAP for SVM speaker recognition

This paper presents Scatter Difference Nuisance Attribute Projection (SD-NAP) as an enhancement to NAP for SVM-based speaker verification. While standard NAP may inadvertently remove desirable speaker variability, SD-NAP explicitly de-emphasises this variability by incorporating a weighted version of the between-class scatter into the NAP optimisation criterion. Experimental evaluation of SD-NAP with a variety of SVM systems on the 2006 and 2008 NIST SRE corpora demonstrate that SD-NAP provides improved verification performance over standard NAP in most cases, particularly at the EER operating point.

Seeing pedestrians at night : visual clutter does not mask biological motion

Although placing reflective markers on pedestrians’ major joints can make pedestrians more conspicuous to drivers at night, it has been suggested that this “biological motion” effect may be reduced when visual clutter is present. We tested whether extraneous points of light affected the ability of 12 younger and 12 older drivers to see pedestrians as they drove on a closed road at night. Pedestrians wore black clothing alone or with retroreflective markings in four different configurations. One pedestrian walked in place and was surrounded by clutter on half of the trials. Another was always surrounded by visual clutter but either walked in place or stood still. Clothing configuration, pedestrian motion, and driver age influenced conspicuity but clutter did not. The results confirm that even in the presence of visual clutter pedestrians wearing biological motion configurations are recognized more often and at greater distances than when they wear a reflective vest.

A brush with the real world : the future of inertial motion capture in live performance

3D Motion capture is a medium that plots motion, typically human motion, converting it into a form that can be represented digitally. It is a fast evolving field and recent inertial technology may provide new artistic possibilities for its use in live performance. Although not often used in this context, motion capture has a combination of attributes that can provide unique forms of collaboration with performance arts. The inertial motion capture suit used for this study has orientation sensors placed at strategic points on the body to map body motion. Its portability, real-time performance, ease of use, and its immunity from line-of-sight problems inherent in optical systems suggest it would work well as a live performance technology. Many animation techniques can be used in real-time. This research examines a broad cross-section of these techniques using four practice-led cases to assess the suitability of inertial motion capture to live performance. Although each case explores different visual possibilities, all make use of the performativity of the medium, using either an improvisational format or interactivity among stage, audience and screen that would be difficult to emulate any other way. A real-time environment is not capable of reproducing the depth and sophistication of animation people have come to expect through media. These environments take many hours to render. In time the combination of what can be produced in real-time and the tools available in a 3D environment will no doubt create their own tree of aesthetic directions in live performance. The case study looks at the potential of interactivity that this technology offers.