@InProceedings{mortensen-EtAl:2020:LREC,
  author    = {Mortensen, David R.  and  Li, Xinjian  and  Littell, Patrick  and  Michaud, Alexis  and  Rijhwani, Shruti  and  Anastasopoulos, Antonios  and  Black, Alan W  and  Metze, Florian  and  Neubig, Graham},
  title     = {AlloVera: A Multilingual Allophone Database},
  booktitle      = {Proceedings of The 12th Language Resources and Evaluation Conference},
  month          = {May},
  year           = {2020},
  address        = {Marseille, France},
  publisher      = {European Language Resources Association},
  pages     = {5329--5336},
  abstract  = {We introduce a new resource, AlloVera, which provides mappings from 218 allophones to phonemes for 14 languages. Phonemes are contrastive phonological units, and allophones are their various concrete realizations, which are predictable from phonological context. While phonemic representations are language specific, phonetic representations (stated in terms of (allo)phones) are much closer to a universal (language-independent) transcription. AlloVera allows the training of speech recognition models that output phonetic transcriptions in the International Phonetic Alphabet (IPA), regardless of the input language. We show that a “universal” allophone model, Allosaurus, built with AlloVera, outperforms “universal” phonemic models and language-specific models on a speech-transcription task. We explore the implications of this technology (and related technologies) for the documentation of endangered and minority languages. We further explore other applications for which AlloVera will be suitable as it grows, including phonological typology.},
  url       = {https://www.aclweb.org/anthology/2020.lrec-1.656}
}