Human and automatic accent identification of Nguni and Sotho Black South African English

Simple item page
dc.contributor.authorDe Wet, F.en_ZA
dc.contributor.authorLouw, P.en_ZA
dc.contributor.authorNiesler, T.en_ZA
dc.date.accessioned2011-05-15T15:55:13Z
dc.date.available2011-05-15T15:55:13Z
dc.date.issued2007
dc.descriptionCITATION: De Wet, F., Louw, P. & Niesler, T. 2007. Human and automatic accent identification of Nguni and Sotho Black South African English. South African Journal of Science, 103(3-4):159-164.
dc.descriptionThe original publication is available at https://journals.co.za
dc.description.abstractIt 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.
dc.description.urihttps://journals.co.za/content/sajsci/103/3-4/EJC96654
dc.description.versionPublisher's version
dc.format.extent6 pages
dc.identifier.citationDe Wet, F., Louw, P. & Niesler, T. 2007. Human and automatic accent identification of Nguni and Sotho Black South African English. South African Journal of Science, 103(3-4):159-164
dc.identifier.issn1996-7489 (online)
dc.identifier.issn0038-2353 (print)
dc.identifier.urihttp://hdl.handle.net/10019.1/9646
dc.language.isoen_ZAen_ZA
dc.publisherAcademy of Science of South Africa
dc.rights.holderAuthor retains copyright
dc.subjectAccents and accentuation
dc.subjectEnglish language -- Accents and accentuation
dc.titleHuman and automatic accent identification of Nguni and Sotho Black South African Englishen_ZA
dc.typeArticle
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
dewet_human_2007.pdf
Size:
243.86 KB
Format:
Adobe Portable Document Format
Description:
Download article
Download
Collections
Research Articles (English)