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.

QUT speaker identity verification system for EVALITA 2009

This document outlines the system submitted by the Speech and Audio Research Laboratory at the Queensland University of Technology (QUT) for the Speaker Identity Verication: Application task of EVALITA 2009. This submission consisted of a score-level fusion of three component systems, a joint-factor GMM system and two SVM systems using GLDS and GMM supervector kernels. Development and evaluation results are presented, demonstrating the effectiveness of this fused system approach.

QUT Speaker Identity Verification system for EVALITA 2009

This document outlines the system submitted by the Speech and Audio Research Laboratory at the Queensland University of Technology (QUT) for the Speaker Identity Verification: Application task of EVALITA 2009. This competitive submission consisted of a score-level fusion of three component systems; a joint-factor analysis GMM system and two SVM systems using GLDS and GMM supervector kernels. Development evaluation and post-submission results are presented in this study, demonstrating the effectiveness of this fused system approach. This study highlights the challenges associated with system calibration from limited development data and that mismatch between training and testing conditions continues to be a major source of error in speaker verification technology.

Improved GMM-based speaker verification using SVM-driven impostor dataset selection

The problem of impostor dataset selection for GMM-based speaker verification is addressed through the recently proposed data-driven background dataset refinement technique. The SVM-based refinement technique selects from a candidate impostor dataset those examples that are most frequently selected as support vectors when training a set of SVMs on a development corpus. This study demonstrates the versatility of dataset refinement in the task of selecting suitable impostor datasets for use in GMM-based speaker verification. The use of refined Z- and T-norm datasets provided performance gains of 15% in EER in the NIST 2006 SRE over the use of heuristically selected datasets. The refined datasets were shown to generalise well to the unseen data of the NIST 2008 SRE.

Data-driven impostor selection for T-norm score normalisation and the background dataset in SVM-based speaker verification

A data-driven background dataset refinement technique was recently proposed for SVM based speaker verification. This method selects a refined SVM background dataset from a set of candidate impostor examples after individually ranking examples by their relevance. This paper extends this technique to the refinement of the T-norm dataset for SVM-based speaker verification. The independent refinement of the background and T-norm datasets provides a means of investigating the sensitivity of SVM-based speaker verification performance to the selection of each of these datasets. Using refined datasets provided improvements of 13% in min. DCF and 9% in EER over the full set of impostor examples on the 2006 SRE corpus with the majority of these gains due to refinement of the T-norm dataset. Similar trends were observed for the unseen data of the NIST 2008 SRE.

Improving automatic speaker verification using SVM techniques

Automatic recognition of people is an active field of research with important forensic and security applications. In these applications, it is not always possible for the subject to be in close proximity to the system. Voice represents a human behavioural trait which can be used to recognise people in such situations. Automatic Speaker Verification (ASV) is the process of verifying a persons identity through the analysis of their speech and enables recognition of a subject at a distance over a telephone channel { wired or wireless. A significant amount of research has focussed on the application of Gaussian mixture model (GMM) techniques to speaker verification systems providing state-of-the-art performance. GMM's are a type of generative classifier trained to model the probability distribution of the features used to represent a speaker. Recently introduced to the field of ASV research is the support vector machine (SVM). An SVM is a discriminative classifier requiring examples from both positive and negative classes to train a speaker model. The SVM is based on margin maximisation whereby a hyperplane attempts to separate classes in a high dimensional space. SVMs applied to the task of speaker verification have shown high potential, particularly when used to complement current GMM-based techniques in hybrid systems. This work aims to improve the performance of ASV systems using novel and innovative SVM-based techniques. Research was divided into three main themes: session variability compensation for SVMs; unsupervised model adaptation; and impostor dataset selection. The first theme investigated the differences between the GMM and SVM domains for the modelling of session variability | an aspect crucial for robust speaker verification. Techniques developed to improve the robustness of GMMbased classification were shown to bring about similar benefits to discriminative SVM classification through their integration in the hybrid GMM mean supervector SVM classifier. Further, the domains for the modelling of session variation were contrasted to find a number of common factors, however, the SVM-domain consistently provided marginally better session variation compensation. Minimal complementary information was found between the techniques due to the similarities in how they achieved their objectives. The second theme saw the proposal of a novel model for the purpose of session variation compensation in ASV systems. Continuous progressive model adaptation attempts to improve speaker models by retraining them after exploiting all encountered test utterances during normal use of the system. The introduction of the weight-based factor analysis model provided significant performance improvements of over 60% in an unsupervised scenario. SVM-based classification was then integrated into the progressive system providing further benefits in performance over the GMM counterpart. Analysis demonstrated that SVMs also hold several beneficial characteristics to the task of unsupervised model adaptation prompting further research in the area. In pursuing the final theme, an innovative background dataset selection technique was developed. This technique selects the most appropriate subset of examples from a large and diverse set of candidate impostor observations for use as the SVM background by exploiting the SVM training process. This selection was performed on a per-observation basis so as to overcome the shortcoming of the traditional heuristic-based approach to dataset selection. Results demonstrate the approach to provide performance improvements over both the use of the complete candidate dataset and the best heuristically-selected dataset whilst being only a fraction of the size. The refined dataset was also shown to generalise well to unseen corpora and be highly applicable to the selection of impostor cohorts required in alternate techniques for speaker verification.

Data-driven background dataset selection for SVM-based speaker verification

The recently proposed data-driven background dataset refinement technique provides a means of selecting an informative background for support vector machine (SVM)-based speaker verification systems. This paper investigates the characteristics of the impostor examples in such highly-informative background datasets. Data-driven dataset refinement individually evaluates the suitability of candidate impostor examples for the SVM background prior to selecting the highest-ranking examples as a refined background dataset. Further, the characteristics of the refined dataset were analysed to investigate the desired traits of an informative SVM background. The most informative examples of the refined dataset were found to consist of large amounts of active speech and distinctive language characteristics. The data-driven refinement technique was shown to filter the set of candidate impostor examples to produce a more disperse representation of the impostor population in the SVM kernel space, thereby reducing the number of redundant and less-informative examples in the background dataset. Furthermore, data-driven refinement was shown to provide performance gains when applied to the difficult task of refining a small candidate dataset that was mis-matched to the evaluation conditions.

Machine prognostics based on health state estimation using SVM

The ability to accurately predict the remaining useful life of machine components is critical for machine continuous operation, and can also improve productivity and enhance system safety. In condition-based maintenance (CBM), maintenance is performed based on information collected through condition monitoring and an assessment of the machine health. Effective diagnostics and prognostics are important aspects of CBM for maintenance engineers to schedule a repair and to acquire replacement components before the components actually fail. All machine components are subjected to degradation processes in real environments and they have certain failure characteristics which can be related to the operating conditions. This paper describes a technique for accurate assessment of the remnant life of machines based on health state probability estimation and involving historical knowledge embedded in the closed loop diagnostics and prognostics systems. The technique uses a Support Vector Machine (SVM) classifier as a tool for estimating health state probability of machine degradation, which can affect the accuracy of prediction. To validate the feasibility of the proposed model, real life historical data from bearings of High Pressure Liquefied Natural Gas (HP-LNG) pumps were analysed and used to obtain the optimal prediction of remaining useful life. The results obtained were very encouraging and showed that the proposed prognostic system based on health state probability estimation has the potential to be used as an estimation tool for remnant life prediction in industrial machinery.

A direct integration scheme for battery-supercapacitor hybrid energy storage systems with the use of grid side inverter

Battery-supercapacitor hybrid energy storage systems are becoming popular in the renewable energy sector due to their improved power and energy performances. These hybrid systems require separate dc-dc converters, or at least one dc-dc converter for the supercapacitor bank, to connect them to the dc-link of the grid interfacing inverter. These additional dc-dc converters increase power losses, complexity and cost. Therefore, possibility of their direct connection is investigated in this paper. The inverter system used in this study is formed by cascading two 3-level inverters, named as the “main inverter” and the “auxiliary inverter”, through a coupling transformer. In the test system the main inverter is connected with the rectified output of a wind generator while the auxiliary inverter is directly attached to a battery and a supercapacitor bank. The major issues with this approach are the dynamic changes in dc-link voltages and inevitable imbalances in the auxiliary inverter voltages, which results in unevenly distributed space vectors. A modified SVM technique is proposed to solve this issue. A PWM based time sharing method is proposed for power sharing between the battery and the supercapacitor. Simulation results are presented to verify the efficacy of the proposed modulation and control techniques.

Space vector modulated cascade multi-level inverter for PMSG wind generation systems

Modulation and control of a cascade multilevel inverter, which has a high potential in future wind generation applications, are presented. The inverter is a combination of a high power, three level “bulk inverter” and a low power “conditioning inverter”. To minimize switching losses, the bulk inverter operates at a low frequency producing square wave outputs while high frequency conditioning inverter is used to suppress harmonic content produced by the bulk inverter output. This paper proposes an improved Space Vector Modulation (SVM) algorithm and a neutral point potential balancing technique for the inverter. Furthermore, a maximum power tracking controller for the Permanent Magnet Synchronous Generator (PMSG) is described in detail. The proposed SVM technique eliminates most of the computational burdens on the digital controller and renders a greater controllability under varying DC-link voltage conditions. The DC-link capacitor voltage balancing of both bulk and conditioning inverters is carried out using Redundant State Selection (RSS) method and is explained in detail. Experimental results are presented to verify the proposed modulation and control techniques.

Comparison of Multiclass SVM Classification Methods to Use in a Supportive System for Distance Relay Coordination

This paper aims at evaluating the methods of multiclass support vector machines (SVMs) for effective use in distance relay coordination. Also, it describes a strategy of supportive systems to aid the conventional protection philosophy in combating situations where protection systems have maloperated and/or information is missing and provide selective and secure coordinations. SVMs have considerable potential as zone classifiers of distance relay coordination. This typically requires a multiclass SVM classifier to effectively analyze/build the underlying concept between reach of different zones and the apparent impedance trajectory during fault. Several methods have been proposed for multiclass classification where typically several binary SVM classifiers are combined together. Some authors have extended binary SVM classification to one-step single optimization operation considering all classes at once. In this paper, one-step multiclass classification, one-against-all, and one-against-one multiclass methods are compared for their performance with respect to accuracy, number of iterations, number of support vectors, training, and testing time. The performance analysis of these three methods is presented on three data sets belonging to training and testing patterns of three supportive systems for a region and part of a network, which is an equivalent 526-bus system of the practical Indian Western grid.

An intelligent approach using support vector machines for monitoring and identification of faults on transmission systems

Power system disturbances are often caused by faults on transmission lines. When faults occur in a power system, the protective relays detect the fault and initiate tripping of appropriate circuit breakers, which isolate the affected part from the rest of the power system. Generally Extra High Voltage (EHV) transmission substations in power systems are connected with multiple transmission lines to neighboring substations. In some cases mal-operation of relays can happen under varying operating conditions, because of inappropriate coordination of relay settings. Due to these actions the power system margins for contingencies are decreasing. Hence, power system protective relaying reliability becomes increasingly important. In this paper an approach is presented using Support Vector Machine (SVM) as an intelligent tool for identifying the faulted line that is emanating from a substation and finding the distance from the substation. Results on 24-bus equivalent EHV system, part of Indian southern grid, are presented for illustration purpose. This approach is particularly important to avoid mal-operation of relays following a disturbance in the neighboring line connected to the same substation and assuring secure operation of the power systems.

Prediction of Queue Waiting Times for Metascheduling on Parallel Batch Systems

Prediction of queue waiting times of jobs submitted to production parallel batch systems is important to provide overall estimates to users and can also help meta-schedulers make scheduling decisions. In this work, we have developed a framework for predicting ranges of queue waiting times for jobs by employing multi-class classification of similar jobs in history. Our hierarchical prediction strategy first predicts the point wait time of a job using dynamic k-Nearest Neighbor (kNN) method. It then performs a multi-class classification using Support Vector Machines (SVMs) among all the classes of the jobs. The probabilities given by the SVM for the class predicted using k-NN and its neighboring classes are used to provide a set of ranges of predicted wait times with probabilities. We have used these predictions and probabilities in a meta-scheduling strategy that distributes jobs to different queues/sites in a multi-queue/grid environment for minimizing wait times of the jobs. Experiments with different production supercomputer job traces show that our prediction strategies can give correct predictions for about 77-87% of the jobs, and also result in about 12% improved accuracy when compared to the next best existing method. Experiments with our meta-scheduling strategy using different production and synthetic job traces for various system sizes, partitioning schemes and different workloads, show that the meta-scheduling strategy gives much improved performance when compared to existing scheduling policies by reducing the overall average queue waiting times of the jobs by about 47%.

Hybrid Working Set Algorithm for SVM Learning With a Kernel Coprocessor on FPGA

Support vector machines (SVM) are a popular class of supervised models in machine learning. The associated compute intensive learning algorithm limits their use in real-time applications. This paper presents a fully scalable architecture of a coprocessor, which can compute multiple rows of the kernel matrix in parallel. Further, we propose an extended variant of the popular decomposition technique, sequential minimal optimization, which we call hybrid working set (HWS) algorithm, to effectively utilize the benefits of cached kernel columns and the parallel computational power of the coprocessor. The coprocessor is implemented on Xilinx Virtex 7 field-programmable gate array-based VC707 board and achieves a speedup of upto 25x for kernel computation over single threaded computation on Intel Core i5. An application speedup of upto 15x over software implementation of LIBSVM and speedup of upto 23x over SVMLight is achieved using the HWS algorithm in unison with the coprocessor. The reduction in the number of iterations and sensitivity of the optimization time to variation in cache size using the HWS algorithm are also shown.

The image coding scheme based on neural network and SVM

This paper applies data coding thought, which based on the virtual information source modeling put forward by the author, to propose the image coding (compression) scheme based on neural network and SVM. This scheme is composed by "the image coding (compression) scheme based oil SVM" embedded "the lossless data compression scheme based oil neural network". The experiments show that the scheme has high compression ratio under the slightly damages condition, partly solve the contradiction which 'high fidelity' and 'high compression ratio' cannot unify in image coding system.