Author:Badenhorst, J; Davel, MH; Barnard, EDate:Nov 2010The authors investigate several approaches aimed at a more detailed understanding of co-articulation in spoken utterances. They find that the Euclidean difference between instantaneous frame-based feature values and the mean values of these ...Read more
Author:Barnard, E; Gouws, E; Wolvaardt, K; Kleynhans, NDate:Nov 2004A number of issues realted to the development of speech-recognition systems with Hidden Markov Models (HMM) are discussed. A set of systematic experiments using the HTK toolkit and the TMIT database are used to elucidate matters such as the ...Read more
Author:Van Dyk, E; Barnard, EDate:Nov 2008We investigate the use of Naive Bayesian classifiers for correlated Gaussian feature spaces and derive error estimates for these classifiers. The error analysis is done by developing an exact expression for the error performance of a binary ...Read more
Author:Kleynhans, N; Barnard, EDate:Nov 2008The performance of trainable speech-processing systems deteriorates significantly when there is a mismatch between the training and testing data. The data mismatch becomes a dominant factor when collecting speech data for resource scarce ...Read more
Author:Kgampe, M; Davel, MHDate:Nov 2010The authors investigate the consistency with which speakers with different language profiles are able to pronounce personal names from Afrikaans, English, Setswana and isiZulu. They gather data in a controlled research study and analyse ...Read more
Author:Cronje, JDate:Nov 2015The work in this paper address the problem of removing non-uniform motion blur from a single image. The motion vector for an image patch is estimated by using a convolutional neural network (CNN). All the predicted motion vectors are combined ...Read more
Author:Govender, Natasha; Barnard, E; Davel, MDate:Nov 2005In order to bring the tools of statistical pattern recognition to bear on intonation modelling, we need tailor-made corpora in the languages of interest. We describe how two such corpora were developed (for isiZulu and isiXhosa, respectively). ...Read more
Author:Mzila, P; Dube, EDate:Jul 2013As internet usage rapidly increases in both private and corporate sectors, the study of network intrusion detection is continuously becoming more relevant and has thus been evolving substantially in recent years. One of the most interesting ...Read more
Author:De Villiers, J; Wilson, F; Nicolls, FDate:Nov 2011A variety of lens distortion modelling techniques exist. Since they make use of different calibration metrics it is difficult to select one over the others. This work aims to compare lens distortion modelling techniques and calibration patterns ...Read more
Author:Martirosian, O; Davel, MDate:Nov 2007The authors explore pattern recognition techniques for verifying the correctness of a pronunciation lexicon, focusing on techniques that require limited human interaction. They evaluate the British English Example Pronunciation (BEEP) dictionary ...Read more
Author:Dorasamy, Kribashnee; Webb-Ray, Leandra; Tapamo, J-RDate:Dec 2016Overcoming small inter-class variation when fingerprints have missing singular points (SPs) is one of the current challenges faced in fingerprint classification, since class information is scarce. Grouping the orientation fields to form ...Read more
Author:Govender, Natasha; Claassens, JDate:Nov 2010For a robotic platform to be able to assist/interact in human environments, the platform must be able to perform some fundamental tasks. This includes interacting with humans by grasping or releasing objects as or when required by the human. ...Read more
Author:Van der Walt, CM; Barnard, EDate:Dec 2013We investigate the performance of conventional bandwidth estimators for non-parametric kernel density estimation on a number of representative pattern-recognition tasks, to gain a better understanding of the behaviour of these estimators in ...Read more
Author:Badenhorst, Jacob AC; De Wet, FebeDate:Nov 2017This paper reports on the recognition of second language (L2) isiXhosa speech produced by beginner level adult language learners. The speech samples were produced and recorded during the development of a Mobile Assisted Language Learning ...Read more
Author:Van der Walt, Christiaan M; Barnard, EDate:Nov 2007The authors study the relationship between the properties of data and classifier performance. Data measures are employed to characterise classification problems and it is shown that these data measures successfully capture important characteristics ...Read more
Author:Coetzee, L; Viviers, I; Barnard, EDate:Dec 2009Multi-modal human computer interfaces are becoming increasingly widespread, building on more capable and affordable devices along with advances in helper applications utilising advanced pattern recognition. These interfaces promise to improve ...Read more
Author:Davel, M; Barnard, EDate:Nov 2005In this paper the authors describe a new approach to rewrite rule extraction and analysis, using Minimal Representation Graphs. This approach provides a mechanism for obtaining the smallest possible rule set – within a context-dependent rewrite ...Read more
Author:Coetzee, L; Barnard, EDate:Nov 2004This paper analyses a number of disabilities, their assistive devices and the associated technologies in order to highlight the role pattern recognition plays in enabling accessibility and improving human computer interaction for people living ...Read more
Author:Aharonson, V; Schlesinger, I; McDonald, Andre M; Dubowsky, S; Korczyn, ADDate:Feb 2018We present PAMM II, the Personal Aid for Mobility and Monitoring II, an instrumented walker for Parkinson’s Disease (PD) patients’ gait monitoring. The objective of the walker is to aid in the diagnosis and monitoring of PD progression as ...Read more
Author:Kgampe, M; Davel, MHDate:Nov 2011Personal names are often pronounced in very different ways depending on the language background of the speaker. We seek to determine whether some of these pronunciations ‘errors’ are systematic and if so, in which ways. Specifically, we analyze ...Read more