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.

Automatic spoken language identification utilizing acoustic and phonetic speech information

Automatic spoken Language Identi¯cation (LID) is the process of identifying the language spoken within an utterance. The challenge that this task presents is that no prior information is available indicating the content of the utterance or the identity of the speaker. The trend of globalization and the pervasive popularity of the Internet will amplify the need for the capabilities spoken language identi¯ca- tion systems provide. A prominent application arises in call centers dealing with speakers speaking di®erent languages. Another important application is to index or search huge speech data archives and corpora that contain multiple languages. The aim of this research is to develop techniques targeted at producing a fast and more accurate automatic spoken LID system compared to the previous National Institute of Standards and Technology (NIST) Language Recognition Evaluation. Acoustic and phonetic speech information are targeted as the most suitable fea- tures for representing the characteristics of a language. To model the acoustic speech features a Gaussian Mixture Model based approach is employed. Pho- netic speech information is extracted using existing speech recognition technol- ogy. Various techniques to improve LID accuracy are also studied. One approach examined is the employment of Vocal Tract Length Normalization to reduce the speech variation caused by di®erent speakers. A linear data fusion technique is adopted to combine the various aspects of information extracted from speech. As a result of this research, a LID system was implemented and presented for evaluation in the 2003 Language Recognition Evaluation conducted by the NIST.

Assimilating cell sheets and hybrid scaffolds for dermal tissue engineering

Cell sheets can be used to produce neo-tissue with mature extracellular matrix. However, extensive contraction of cell sheets remains a problem. We devised a technique to overcome this problem and applied it to tissue engineer a dermal construct. Human dermal fibroblasts were cultured with poly(lactic-co-glycolic acid)-collagen meshes and collagen-hyaluronic acid foams. Resulting cell sheets were folded over the scaffolds to form dermal constructs. Human keratinocytes were cultured on these dermal constructs to assess their ability to support bilayered skin regeneration. Dermal constructs produced with collagen-hyaluronic acid foams showed minimal contraction, while those with poly(lactic-co-glycolic acid)-collagen meshes curled up. Cell proliferation and metabolic activity profiles were characterized with PicoGreen and AlamarBlue assays, respectively. Fluorescent labeling showed high cell viability and F-actin expression within the constructs. Collagen deposition was detected by immunocytochemistry and electron microscopy. Transforming Growth Factor-alpha and beta1, Keratinocyte Growth Factor and Vascular Endothelial Growth Factor were produced at various stages of culture, measured by RT-PCR and ELISA. These results indicated that assimilating cell sheets with mechanically stable scaffolds could produce viable dermal-like constructs that do not contract. Repeated enzymatic treatment cycles for cell expansion is unnecessary, while the issue of poor cell seeding efficiency in scaffolds is eliminated.

An alginate-based hybrid system for growth factor delivery in the functional repair of large bone defects

The treatment of challenging fractures and large osseous defects presents a formidable problem for orthopaedic surgeons. Tissue engineering/regenerative medicine approaches seek to solve this problem by delivering osteogenic signals within scaffolding biomaterials. In this study, we introduce a hybrid growth factor delivery system that consists of an electrospun nanofiber mesh tube for guiding bone regeneration combined with peptide-modified alginate hydrogel injected inside the tube for sustained growth factor release. We tested the ability of this system to deliver recombinant bone morphogenetic protein-2 (rhBMP-2) for the repair of critically-sized segmental bone defects in a rat model. Longitudinal [mu]-CT analysis and torsional testing provided quantitative assessment of bone regeneration. Our results indicate that the hybrid delivery system resulted in consistent bony bridging of the challenging bone defects. However, in the absence of rhBMP-2, the use of nanofiber mesh tube and alginate did not result in substantial bone formation. Perforations in the nanofiber mesh accelerated the rhBMP-2 mediated bone repair, and resulted in functional restoration of the regenerated bone. [mu]-CT based angiography indicated that perforations did not significantly affect the revascularization of defects, suggesting that some other interaction with the tissue surrounding the defect such as improved infiltration of osteoprogenitor cells contributed to the observed differences in repair. Overall, our results indicate that the hybrid alginate/nanofiber mesh system is a promising growth factor delivery strategy for the repair of challenging bone injuries.

Evaluation of a hybrid scaffold/cell construct in repair of high-load-bearing osteochondral defects in rabbits

The objective of this study was to evaluate the feasibility and potential of a hybrid scaffold system in large- and high-load-bearing osteochondral defects repair. The implants were made of medical-grade PCL (mPCL) for the bone compartment whereas fibrin glue was used for the cartilage part. Both matrices were seeded with allogenic bone marrow-derived mesenchymal cells (BMSC) and implanted in the defect (4 mm diameter×5 mm depth) on medial femoral condyle of adult New Zealand White rabbits. Empty scaffolds were used at the control side. Cell survival was tracked via fluorescent labeling. The regeneration process was evaluated by several techniques at 3 and 6 months post-implantation. Mature trabecular bone regularly formed in the mPCL scaffold at both 3 and 6 months post-operation. Micro-Computed Tomography showed progression of mineralization from the host–tissue interface towards the inner region of the grafts. At 3 months time point, the specimens showed good cartilage repair. In contrast, the majority of 6 months specimens revealed poor remodeling and fissured integration with host cartilage while other samples could maintain good cartilage appearance. In vivo viability of the transplanted cells was demonstrated for the duration of 5 weeks. The results demonstrated that mPCL scaffold is a potential matrix for osteochondral bone regeneration and that fibrin glue does not inherit the physical properties to allow for cartilage regeneration in a large and high-load-bearing defect site. Keywords: Osteochondral tissue engineering; Scaffold; Bone marrow-derived precursor cells; Fibrin glue

Hybrid robot control and SLAM for persistent navigation and mapping

For a mobile robot to operate autonomously in real-world environments, it must have an effective control system and a navigation system capable of providing robust localization, path planning and path execution. In this paper we describe the work investigating synergies between mapping and control systems. We have integrated development of a control system for navigating mobile robots and a robot SLAM system. The control system is hybrid in nature and tightly coupled with the SLAM system; it uses a combination of high and low level deliberative and reactive control processes to perform obstacle avoidance, exploration, global navigation and recharging, and draws upon the map learning and localization capabilities of the SLAM system. The effectiveness of this hybrid, multi-level approach was evaluated in the context of a delivery robot scenario. Over a period of two weeks the robot performed 1143 delivery tasks to 11 different locations with only one delivery failure (from which it recovered), travelled a total distance of more than 40km, and recharged autonomously a total of 23 times. In this paper we describe the combined control and SLAM system and discuss insights gained from its successful application in a real-world context.

Automatic generation of assertions to detect potential security vulnerabilities in C programs that use union and pointer types

Type unions, pointer variables and function pointers are a long standing source of subtle security bugs in C program code. Their use can lead to hard-to-diagnose crashes or exploitable vulnerabilities that allow an attacker to attain privileged access over classified data. This paper describes an automatable framework for detecting such weaknesses in C programs statically, where possible, and for generating assertions that will detect them dynamically, in other cases. Exclusively based on analysis of the source code, it identifies required assertions using a type inference system supported by a custom made symbol table. In our preliminary findings, our type system was able to infer the correct type of unions in different scopes, without manual code annotations or rewriting. Whenever an evaluation is not possible or is difficult to resolve, appropriate runtime assertions are formed and inserted into the source code. The approach is demonstrated via a prototype C analysis tool.

The embodied hybrid space : designing ubiquitous computing towards an amplification of situated real world experiences

The emergence of mobile and ubiquitous computing technology has created what is often referred to as the hybrid space – a virtual layer of digital information and interaction opportunities that sit on top of and augment the physical environment. Embodied media materialise digital information as observable and sometimes interactive parts of the physical environment. The aim of this work is to explore ways to enhance people’s situated real world experience, and to find out what the role and impact of embodied media in achieving this goal can be. The Edge, an initiative of the State Library of Queensland in Brisbane, Australia, and case study of this thesis, envisions to be a physical place for people to meet, explore, experience, learn and teach each other creative practices in various areas related to digital technology and arts. Guided by an Action Research approach, this work applies Lefebvre’s triad of space (1991) to investigate the Edge as a social space from a conceived, perceived and lived point of view. Based on its creators’ vision and goals on the conceived level, different embodied media are iteratively designed, implemented and evaluated towards shaping and amplifying the Edge’s visitor experience on the perceived and lived level.