@conference{278,
  keywords = {TTS corpora, multi-speaker and code-switched data, under-resourced languages},
  author = {Daniel Van Niekerk and Charl Van Heerden and Marelie Davel and Neil Kleynhans and Oddur Kjartansson and Martin Jansche and Linne Ha},
  title = {Rapid development of TTS corpora for four South African languages},
  abstract = {This paper describes the development of text-to-speech corpora for four South African languages. The approach followed investigated the possibility of using low-cost methods including informal recording environments and untrained volunteer speakers. This objective and the additional future goal of expanding the corpus to increase coverage of South Africa{\textquoteright}s 11 official languages necessitated experimenting with multi-speaker and code-switched data. The process and relevant observations are detailed throughout. The latest version of the corpora are available for download under an open-source licence and will likely see further development and refinement in future.},
  year = {2017},
  journal = {Interspeech},
  chapter = {2178-2182},
  address = {Stockholm, Sweden},
  doi = {10.21437/Interspeech.2017-1139},
}