Author:Modipa, T; De Wet, Febe; Davel, MDate:Nov 2009Call routing is an important application of Automatic Speech Recognition (ASR) technology. In this paper the authors discuss the main issues affecting the performance of a call routing system and describe the ASR component of the "AutoSecretary" ...Read more
Author:Van Heerden, C; Barnard, EDate:Nov 2009The authors compare several different classifier combination methods on a single task, namely speaker age classification. This task is well suited to combination strategies, since significantly different feature classes are employed. Support ...Read more
Author:Loots, L; Davel, M; Barnard, E; Niesler, TDate:Nov 2009Phoneme-to-phoneme (P2P) learning provides a mechanism for predicting the pronunciation of a word based on its pronunciation in a different accent, dialect or language. The authors evaluate the effectiveness of manually-developed as well as ...Read more
Author:Burke, Michael GDate:Nov 2009This poster presents a visual servo approach to straight line range and velocity regulation. The difference in velocity between a lead mobile robot and a follower is regulated through velocity control of the follower, in order to maintain a ...Read more
Author:Rens, GB; Varzinczak, IJDate:Dec 2009The authors are developing a new logic (DyMoDeL) for reasoning about dynamic agents with stochastic action, partial observation, knowledge-of and degree-of-belief-in a state of affairs. Development of the syntax and semantics is almost complete, ...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:Van Niekerk, DR; Barnard, E; Schlunz, Georg IDate:Nov 2009With the increasing prominence and maturity of corpus-based techniques for speech synthesis, the process of system development has in some ways been simplified considerably. However, the dependence on sufficient amounts of relevant speech ...Read more
Author:Bachoo, AKDate:Dec 2009Within the context of video surveillance, object and incident detection by an operator is minimized in over- and under-exposed pixels. Multiple different exposures of the same scene can be fused to create a well-balanced and detailed image ...Read more
Author:Van Huyssteen, GB; Pilon, SDate:Nov 2009For fast-tracking the development of resources for resource-scarce languages, one could transfer existing technologies from one language to another well-sourced, closely-related language. In this contribution, the authors describe the development ...Read more