@article{280,
  keywords = {Speech corpus collection, Pronunciation modelling, Speech recognition, Proper names},
  author = {Jan Thirion and Charl Van Heerden and Oluwapelumi Giwa and Marelie Davel},
  title = {The South African directory enquiries (SADE) name corpus},
  abstract = {We present the design and development of a South African directory enquiries corpus. It contains audio and orthographic transcriptions of a wide range of South African names produced by first-language speakers of four languages, namely Afrikaans, English, isiZulu and Sesotho. Useful as a resource to understand the effect of name language and speaker language on pronunciation, this is the first corpus to also aim to identify the ‘‘intended language’’: an implicit assumption with regard to word origin made by the speaker of the name. We describe the design, collection, annotation, and verification of the corpus. This includes an analysis of the algorithms used to tag the corpus with meta information that may be beneficial to pronunciation modelling tasks.},
  year = {2020},
  journal = {Language Resources & Evaluation},
  volume = {54},
  chapter = {155-184},
  publisher = {Springer},
  address = {Cape Town, South Africa},
  doi = {10.1007/s10579-019-09448-6},
}