Speaker verification using I-vector features

This PhD research has provided novel solutions to three major challenges which have prevented the wide spread deployment of speaker recognition technology: (1) combating enrolment/ verification mismatch, (2) reducing the large amount of development and training data that is required and (3) reducing the duration of speech required to verify a speaker. A range of applications of speaker recognition technology from forensics in criminal investigations to secure access in banking will benefit from the research outcomes.

Veracity of the archive : a research approach to the collection and verification of urban morphological records using qualitative data analysis software

Critical to the research of urban morphologists is the availability of historical records that document the urban transformation of the study area. However, thus far little work has been done towards an empirical approach to the validation of archival data in this field. Outlined in this paper, therefore, is a new methodology for validating the accuracy of archival records and mapping data, accrued through the process of urban morphological research, so as to establish a reliable platform from which analysis can proceed. The paper particularly addresses the problems of inaccuracies in existing curated historical information, as well as errors in archival research by student assistants, which together give rise to unacceptable levels of uncertainty in the documentation. The paper discusses the problems relating to the reliability of historical information, demonstrates the importance of data verification in urban morphological research, and proposes a rigorous method for objective testing of collected archival data through the use of qualitative data analysis software.

Improving out-domain PLDA speaker verification using unsupervised inter-dataset variability compensation approach

Experimental studies have found that when the state-of-the-art probabilistic linear discriminant analysis (PLDA) speaker verification systems are trained using out-domain data, it significantly affects speaker verification performance due to the mismatch between development data and evaluation data. To overcome this problem we propose a novel unsupervised inter dataset variability (IDV) compensation approach to compensate the dataset mismatch. IDV-compensated PLDA system achieves over 10% relative improvement in EER values over out-domain PLDA system by effectively compensating the mismatch between in-domain and out-domain data.

Improving PLDA speaker verification using WMFD and linear-weighted approaches in limited microphone data conditions

This paper proposes the addition of a weighted median Fisher discriminator (WMFD) projection prior to length-normalised Gaussian probabilistic linear discriminant analysis (GPLDA) modelling in order to compensate the additional session variation. In limited microphone data conditions, a linear-weighted approach is introduced to increase the influence of microphone speech dataset. The linear-weighted WMFD-projected GPLDA system shows improvements in EER and DCF values over the pooled LDA- and WMFD-projected GPLDA systems in inter-view-interview condition as WMFD projection extracts more speaker discriminant information with limited number of sessions/ speaker data, and linear-weighted GPLDA approach estimates reliable model parameters with limited microphone data.

Dataset-invariant covariance normalization for out-domain PLDA speaker verification

In this paper we introduce a novel domain-invariant covariance normalization (DICN) technique to relocate both in-domain and out-domain i-vectors into a third dataset-invariant space, providing an improvement for out-domain PLDA speaker verification with a very small number of unlabelled in-domain adaptation i-vectors. By capturing the dataset variance from a global mean using both development out-domain i-vectors and limited unlabelled in-domain i-vectors, we could obtain domain- invariant representations of PLDA training data. The DICN- compensated out-domain PLDA system is shown to perform as well as in-domain PLDA training with as few as 500 unlabelled in-domain i-vectors for NIST-2010 SRE and 2000 unlabelled in-domain i-vectors for NIST-2008 SRE, and considerable relative improvement over both out-domain and in-domain PLDA development if more are available.

Verification and Operation of Adaptive Materials in Space

Piezoelectric polymers based on polyvinylidene fluoride (PVDF) are of interest as smart materials for novel space-based telescope applications. Dimensional adjustments of adaptive thin polymer films are achieved via controlled charge deposition. Predicting their long-term performance requires a detailed understanding of the piezoelectric property changes that develop during space environmental exposure. The overall materials performance is governed by a combination of chemical and physical degradation processes occurring in low Earth orbit as established by our past laboratory-based materials performance experiments (see report SAND 2005-6846). Molecular changes are primarily induced via radiative damage, and physical damage from temperature and atomic oxygen exposure is evident as depoling, loss of orientation and surface erosion. The current project extension has allowed us to design and fabricate small experimental units to be exposed to low Earth orbit environments as part of the Materials International Space Station Experiments program. The space exposure of these piezoelectric polymers will verify the observed trends and their degradation pathways, and provide feedback on using piezoelectric polymer films in space. This will be the first time that PVDF-based adaptive polymer films will be operated and exposed to combined atomic oxygen, solar UV and temperature variations in an actual space environment. The experiments are designed to be fully autonomous, involving cyclic application of excitation voltages, sensitive film position sensors and remote data logging. This mission will provide critically needed feedback on the long-term performance and degradation of such materials, and ultimately the feasibility of large adaptive and low weight optical systems utilizing these polymers in space.

A Pattern Recognition Model of Voice-Based Personal Verification Systems for Forensic Applications

Abstract-The success of automatic speaker recognition in laboratory environments suggests applications in forensic science for establishing the Identity of individuals on the basis of features extracted from speech. A theoretical model for such a verification scheme for continuous normaliy distributed featureIss developed. The three cases of using a) single feature, b)multipliendependent measurements of a single feature, and c)multpleindependent features are explored.The number iofndependent features needed for areliable personal identification is computed based on the theoretcal model and an expklatory study of some speech featues.

Use of electronic portal imaging devices for electron treatment verification

This study aims to help broaden the use of electronic portal imaging devices (EPIDs) for pre-treatment patient positioning verification, from photon-beam radiotherapy to photon- and electron-beam radiotherapy, by proposing and testing a method for acquiring clinicallyuseful EPID images of patient anatomy using electron beams, with a view to enabling and encouraging further research in this area. EPID images used in this study were acquired using all available beams from a linac configured to deliver electron beams with nominal energies of 6, 9, 12, 16 and 20 MeV, as well as photon beams with nominal energies of 6 and 10 MV. A widely-available heterogeneous, approximately-humanoid, thorax phantom was used, to provide an indication of the contrast and noise produced when imaging different types of tissue with comparatively realistic thicknesses. The acquired images were automatically calibrated, corrected for the effects of variations in the sensitivity of individual photodiodes, using a flood field image. For electron beam imaging, flood field EPID calibration images were acquired with and without the placement of blocks of water-equivalent plastic (with thicknesses approximately equal to the practical range of electrons in the plastic) placed upstream of the EPID, to filter out the primary electron beam, leaving only the bremsstrahlung photon signal. While the electron beam images acquired using a standard (unfiltered) flood field calibration were observed to be noisy and difficult to interpret, the electron beam images acquired using the filtered flood field calibration showed tissues and bony anatomy with levels of contrast and noise that were similar to the contrast and noise levels seen in the clinically acceptable photon beam EPID images. The best electron beam imaging results (highest contrast, signal-to-noise and contrast-to-noise ratios) were achieved when the images were acquired using the higher energy electron beams (16 and 20 MeV) when the EPID was calibrated using an intermediate (12 MeV) electron beam energy. These results demonstrate the feasibility of acquiring clinically-useful EPID images of patient anatomy using electron beams and suggest important avenues for future investigation, thus enabling and encouraging further research in this area. There is manifest potential for the EPID imaging method proposed in this work to lead to the clinical use of electron beam imaging for geometric verification of electron treatments in the future.

A computational algorithm for the verification of tautologies in propositional calculus

A computational algorithm (based on Smullyan's analytic tableau method) that varifies whether a given well-formed formula in propositional calculus is a tautology or not has been implemented on a DEC system 10. The stepwise refinement approch of program development used for this implementation forms the subject matter of this paper. The top-down design has resulted in a modular and reliable program package. This computational algoritlhm compares favourably with the algorithm based on the well-known resolution principle used in theorem provers.

Forest inventory-based large-scale forest biomass and carbon budget assessment: new enhanced methods and use of remote sensing for verification

In recent years, concern has arisen over the effects of increasing carbon dioxide (CO2) in the earth's atmosphere due to the burning of fossil fuels. One way to mitigate increase in atmospheric CO2 concentration and climate change is carbon sequestration to forest vegeta-tion through photosynthesis. Comparable regional scale estimates for the carbon balance of forests are therefore needed for scientific and political purposes. The aim of the present dissertation was to improve methods for quantifying and verifying inventory-based carbon pool estimates of the boreal forests in the mineral soils. Ongoing forest inventories provide a data based on statistically sounded sampling for estimating the level of carbon stocks and stock changes, but improved modelling tools and comparison of methods are still needed. In this dissertation, the entire inventory-based large-scale forest carbon stock assessment method was presented together with some separate methods for enhancing and comparing it. The enhancement methods presented here include ways to quantify the biomass of understorey vegetation as well as to estimate the litter production of needles and branches. In addition, the optical remote sensing method illustrated in this dis-sertation can be used to compare with independent data. The forest inventory-based large-scale carbon stock assessment method demonstrated here provided reliable carbon estimates when compared with independent data. Future ac-tivity to improve the accuracy of this method could consist of reducing the uncertainties regarding belowground biomass and litter production as well as the soil compartment. The methods developed will serve the needs for UNFCCC reporting and the reporting under the Kyoto Protocol. This method is principally intended for analysts or planners interested in quantifying carbon over extensive forest areas.

Feature extraction for fingerprint classification

This paper presents two algorithms for smoothing and feature extraction for fingerprint classification. Deutsch's(2) Thinning algorithm (rectangular array) is used for thinning the digitized fingerprint (binary version). A simple algorithm is also suggested for classifying the fingerprints. Experimental results obtained using such algorithms are presented.

Deploying speaker verification techniques to vision-based RPA detect and avoid

Detect and Avoid (DAA) technology is widely acknowledged as a critical enabler for unsegregated Remote Piloted Aircraft (RPA) operations, particularly Beyond Visual Line of Sight (BVLOS). Image-based DAA, in the visible spectrum, is a promising technological option for addressing the challenges DAA presents. Two impediments to progress for this approach are the scarcity of available video footage to train and test algorithms, in conjunction with testing regimes and specifications which facilitate repeatable, statistically valid, performance assessment. This paper includes three key contributions undertaken to address these impediments. In the first instance, we detail our progress towards the creation of a large hybrid collision and near-collision encounter database. Second, we explore the suitability of techniques employed by the biometric research community (Speaker Verification and Language Identification), for DAA performance optimisation and assessment. These techniques include Detection Error Trade-off (DET) curves, Equal Error Rates (EER), and the Detection Cost Function (DCF). Finally, the hybrid database and the speech-based techniques are combined and employed in the assessment of a contemporary, image based DAA system. This system includes stabilisation, morphological filtering and a Hidden Markov Model (HMM) temporal filter.

Verification of the applicability of lattice model to concrete fracture by AE study

Notched three-point bend specimens (TPB) were tested under crack mouth opening displacement (CMOD) control at a rate of 0.0004 mm/s and the entire fracture process was simulated using a regular triangular two-dimensional lattice network only over the expected fracture proces zone width. The rest of the beam specimen was discretised by a coarse triangular finite element mesh. The discrete grain structure of the concrete was generated assuming the grains to be spherical. The load versus CMOD plots thus simulated agreed reasonably well with the experimental results. Moreover, acoustic emission (AE) hits were recorded during the test and compared with the number of fractured lattice elements. It was found that the cumulative AE hits correlated well with the cumulative fractured lattice elements at all load levels thus providing a useful means for predicting when the micro-cracks form during the fracturing process, both in the pre-peak and in the post-peak regimes.