Author:Van Niekerk, DR; Barnard, EDate:Nov 2008The quality of corpus-based text-to-speech (TTS) systems depends strongly on the consistency of boundary placements during phonetic alignments. Expert human transcribers use visually represented acoustic cues in order to consistently place ...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:Badenhorst, JAC; Davel, MDate:Nov 2008When developing speech recognition systems in resource-constrained environments, careful design of the training corpus can play an important role in compensating for data scarcity. One of the factors to consider relates to the speaker composition ...Read more
Author:Louw, Johannes ADate:Nov 2008This paper introduces a new multilingual text-to-speech system, which we call Speect (Speech synthesis with extensible architecture), aiming to address the shortcomings of using Festival as a research sytem and Flite as a deployment system ...Read more
Author:Senekal, FPDate:Nov 2008This paper presents a new technique for the recognition of road traffic signs. The technique is based on colour and shape analysis of a single image. It is aimed at the detection and classification of triangular traffic signs, such as warning ...Read more