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.

Automatic grading and packing of prawns

Prawns are a substantial Australian resource but presently are processed in a very labour-intensive manner. A prototype system has been developed for automatically grading and packing prawns into single-layer 'consumer packs' in which each prawn is approximately straight and has the same orientation. The novel technology includes a machine vision system that has been specially programmed to calculate relevant parameters at high speed and a gripper mechanism that can acquire, straighten and place prawns of various sizes. The system can be implemented on board a trawler or in an onshore processing facility. © 1993.

Automatic calibration of a spiking head-direction network for representing robot orientation

Calibration of movement tracking systems is a difficult problem faced by both animals and robots. The ability to continuously calibrate changing systems is essential for animals as they grow or are injured, and highly desirable for robot control or mapping systems due to the possibility of component wear, modification, damage and their deployment on varied robotic platforms. In this paper we use inspiration from the animal head direction tracking system to implement a self-calibrating, neurally-based robot orientation tracking system. Using real robot data we demonstrate how the system can remove tracking drift and learn to consistently track rotation over a large range of velocities. The neural tracking system provides the first steps towards a fully neural SLAM system with improved practical applicability through selftuning and adaptation.

Audio visual automatic speech recognition in vehicles

Acoustically, car cabins are extremely noisy and as a consequence, existing audio-only speech recognition systems, for voice-based control of vehicle functions such as the GPS based navigator, perform poorly. Audio-only speech recognition systems fail to make use of the visual modality of speech (eg: lip movements). As the visual modality is immune to acoustic noise, utilising this visual information in conjunction with an audio only speech recognition system has the potential to improve the accuracy of the system. The field of recognising speech using both auditory and visual inputs is known as Audio Visual Speech Recognition (AVSR). Continuous research in AVASR field has been ongoing for the past twenty-five years with notable progress being made. However, the practical deployment of AVASR systems for use in a variety of real-world applications has not yet emerged. The main reason is due to most research to date neglecting to address variabilities in the visual domain such as illumination and viewpoint in the design of the visual front-end of the AVSR system. In this paper we present an AVASR system in a real-world car environment using the AVICAR database [1], which is publicly available in-car database and we show that the use of visual speech conjunction with the audio modality is a better approach to improve the robustness and effectiveness of voice-only recognition systems in car cabin environments.

Force-controlled automatic microassembly of tissue engineering scaffolds

This paper presents an automated system for 3D assembly of tissue engineering (TE) scaffolds made from biocompatible microscopic building blocks with relatively large fabrication error. It focuses on the pin-into-hole force control developed for this demanding microassembly task. A beam-like gripper with integrated force sensing at a 3 mN resolution with a 500 mN measuring range is designed, and is used to implement an admittance force-controlled insertion using commercial precision stages. Visual-based alignment followed by an insertion is complemented by a haptic exploration strategy using force and position information. The system demonstrates fully automated construction of TE scaffolds with 50 microparts whose dimension error is larger than 5%.

Submarine automatic control

This paper investigates the automatic atti- tude and depth control of a torpedo shaped submarine. Both experimental results and dynamic simulations are used to tune feed- back control loops in order to obtain stable control of yaw, pitch and roll of the craft.

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.

Automatic in-bucket volume estimation for dragline operations

This paper presents a method for calculating the in-bucket payload volume on a dragline for the purpose of estimating the material’s bulk density in real-time. Knowledge of the bulk density can provide instant feedback to mine planning and scheduling to improve blasting and in turn provide a more uniform bulk density across the excavation site. Furthermore costs and emissions in dragline operation, maintenance and downstream material processing can be reduced. The main challenge is to determine an accurate position and orientation of the bucket with the constraint of real-time performance. The proposed solution uses a range bearing and tilt sensor to locate and scan the bucket between the lift and dump stages of the dragline cycle. Various scanning strategies are investigated for their benefits in this real-time application. The bucket is segmented from the scene using cluster analysis while the pose of the bucket is calculated using the iterative closest point (ICP) algorithm. Payload points are segmented from the bucket by a fixed distance neighbour clustering method to preserve boundary points and exclude low density clusters introduced by overhead chains and the spreader bar. A height grid is then used to represent the payload from which the volume can be calculated by summing over the grid cells. We show volume calculated on a scaled system with an accuracy of greater than 95 per cent.

Approximate Bayesian computation using indirect inference

We present a novel approach for developing summary statistics for use in approximate Bayesian computation (ABC) algorithms by using indirect inference. ABC methods are useful for posterior inference in the presence of an intractable likelihood function. In the indirect inference approach to ABC the parameters of an auxiliary model fitted to the data become the summary statistics. Although applicable to any ABC technique, we embed this approach within a sequential Monte Carlo algorithm that is completely adaptive and requires very little tuning. This methodological development was motivated by an application involving data on macroparasite population evolution modelled by a trivariate stochastic process for which there is no tractable likelihood function. The auxiliary model here is based on a beta–binomial distribution. The main objective of the analysis is to determine which parameters of the stochastic model are estimable from the observed data on mature parasite worms.

Automatic domain ontology extraction for context-sensitive opinion mining

Automated analysis of the sentiments presented in online consumer feedbacks can facilitate both organizations’ business strategy development and individual consumers’ comparison shopping. Nevertheless, existing opinion mining methods either adopt a context-free sentiment classification approach or rely on a large number of manually annotated training examples to perform context sensitive sentiment classification. Guided by the design science research methodology, we illustrate the design, development, and evaluation of a novel fuzzy domain ontology based contextsensitive opinion mining system. Our novel ontology extraction mechanism underpinned by a variant of Kullback-Leibler divergence can automatically acquire contextual sentiment knowledge across various product domains to improve the sentiment analysis processes. Evaluated based on a benchmark dataset and real consumer reviews collected from Amazon.com, our system shows remarkable performance improvement over the context-free baseline.

Design and development of automatic visual inspection system for PCB manufacturing

Inspection of solder joints has been a critical process in the electronic manufacturing industry to reduce manufacturing cost, improve yield, and ensure product quality and reliability. This paper proposes two inspection modules for an automatic solder joint classification system. The “front-end” inspection system includes illumination normalisation, localisation and segmentation. The “back-end” inspection involves the classification of solder joints using the Log Gabor filter and classifier fusion. Five different levels of solder quality with respect to the amount of solder paste have been defined. The Log Gabor filter has been demonstrated to achieve high recognition rates and is resistant to misalignment. This proposed system does not need any special illumination system, and the images are acquired by an ordinary digital camera. This system could contribute to the development of automated non-contact, non-destructive and low cost solder joint quality inspection systems.