Browsing by Author "Louw, P."

Now showing 1 - 2 of 2
  • Thumbnail Image
    Item
    Human and automatic accent identification of Nguni and Sotho Black South African English
    (Academy of Science of South Africa, 2007) De Wet, F.; Louw, P.; Niesler, T.
    It is well established that accent can have a detrimental effect on the performance of automatic speech recognition (ASR) systems. Whereas accents can be labelled in terms of a speaker's mother tongue, it remains to be determined if and when this distinction is appropriate for the development of ASR technology. This study compares the varieties of South African English produced by mother-tongue speakers of the Nguni and Sotho languages, who account for over 70% of the country's population. The aim of the investigation was to determine whether these two accent groups should be treated as a single variety by ASR systems, or whether it is better to consider them separately. To this end, two sets of experiments were carried out. First, a perceptual experiment was performed in which human listeners were required to classify different English accents. Subsequently, automatic speech recognition experiments were conducted to determine how the accuracy of an automatic accent identification system compares with these perceptual results, and whether the acoustic models benefit from the incorporation of Nguni/Sotho accent classifications. The results of the perceptual experiment indicated that most listeners could not correctly identify a speaker's mother tongue based on their English accent. This finding was supported by the results of the automatic accent identification and speech recognition experiments.
  • Thumbnail Image
    Item
    Vital signs for children at triage : a multicentre validation of the revised South African Triage Scale (SATS) for children
    (Health & Medical Publishing Group, 2013-03-22) Twomey, M.; Cheema, B.; Buys, H.; Cohen, K.; De Sa, A.; Louw, P.; Ismail, M.; Finlayson, H.; Cunningham, C.; Westwood, A.
    Objective. To validate a revised version of the paediatric South African Triage Scale (SATS) against admission as a reference standard and compare the sensitivity of triage using: (i) clinical discriminators; (ii) an age-appropriate physiological composite score; and (iii) a combination of both. Methods. A prospective cohort study was undertaken validating the revised paediatric SATS against outcome markers of children at six emergency centres during a 2-month period in 2011. The primary outcome marker was the proportion of children admitted. Validity indicators including sensitivity (Se), specificity, positive predictive value and negative predictive value (NPV) were used to estimate the validity. Associated percentages for over-/under-triage were used to further assess practical application of the paediatric SATS. Results. A total of 2 014 children were included. The percentage of hospital admissions increased with an increase in the level of urgency from 5% in the non-urgent patients to 73% in the emergency patients. The data demonstrated that sensitivity increased substantially when using the SATS, which is a combination of clinical discriminators and the Triage Early Warning Score (TEWS) (Se 91.0%, NPV 95.3%), compared with use of clinical discriminators in isolation (Se 57.1%, NPV 86.3%) or the TEWS in isolation (Se 75.6%, NPV 89.1%). Conclusion. The results of this study illustrate that the revised paediatric SATS is a safe and robust triage tool.