@inproceedings{bamfo-odoom-etal-2024-speech,
    title = "Speech Data from Radio Broadcasts for Low Resource Languages",
    author = "Bamfo Odoom, Bismarck  and
      Paola Garcia Perera, Leibny  and
      Hansanti, Prangthip  and
      Barrault, Loic  and
      Ropers, Christophe  and
      Wiesner, Matthew  and
      Murray, Kenton  and
      Mourachko, Alexandre  and
      Koehn, Philipp",
    editor = "Salesky, Elizabeth  and
      Federico, Marcello  and
      Carpuat, Marine",
    booktitle = "Proceedings of the 21st International Conference on Spoken Language Translation (IWSLT 2024)",
    month = aug,
    year = "2024",
    address = "Bangkok, Thailand (in-person and online)",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/jlcl-multiple-ingestion/2024.iwslt-1.18/",
    doi = "10.18653/v1/2024.iwslt-1.18",
    pages = "134--139",
    abstract = "We created a collection of speech data for 48 low resource languages. The corpus is extracted from radio broadcasts and processed with novel speech detection and language identification models based on a manually vetted subset of the audio for 10 languages. The data is made publicly available."
}