Browsing Faculty of Engineering by Subject "Audio harvesting"

Now showing items 1-1 of 1

Unsupervised acoustic model training: comparing South African English and isiZulu

Kleynhans, Neil; De Wet, Febe; Barnard, Etienne (IEEE, 2015)

Large amounts of untranscribed audio data are generated every day. These audio resources can be used to develop robust acoustic models that can be used in a variety of speech-based systems. Manually transcribing this ...