Reference

Paschen, L., Delafontaine, F., Draxler, C., Fuchs, S., Stave, M., Seifart, F. (2020). Building a Time-Aligned Cross-Linguistic Reference Corpus from Language Documentation Data (DoReCo). In Proceedings of the 12th Conference on Language Resources and Evaluation (pp. 2657-2666).

BibTeX

@inproceedings{paschenBuildingTimeAlignedCrossLinguistic2020,
  title = {{Building a Time-Aligned Cross-Linguistic Reference Corpus from Language Documentation Data (DoReCo)}},
  booktitle = {{Proceedings of the 12th Conference on Language Resources and Evaluation}},
  author = {Paschen, Ludger and Delafontaine, Fran{\c c}ois and Draxler, Christoph and Fuchs, Susanne and Stave, Matthew and Seifart, Frank},
  year = {2020},
  month = may,
  pages = {pg. 2657-2666},
  address = {Marseille},
  abstract = {Natural speech data on many languages have been collected by language documentation projects aiming to preserve linguistic and cultural traditions in audiovisual records. These data hold great potential for large-scale cross-linguistic research into phonetics and language processing. Major obstacles to utilizing such data for typological studies include the non-homogenous nature of file formats and annotation conventions found both across and within archived collections. Moreover, time-aligned audio tran- scriptions are typically only available at the level of broad (multi-word) phrases but not at the word and segment levels. We report on solutions developed for these issues within the DoReCo (DOcumentation REference COrpus) project. DoReCo aims at providing time-aligned transcriptions for at least 50 collections of under-resourced languages. This paper gives a preliminary overview of the current state of the project and details our workflow, in particular standardization of formats and conventions, the addition of segmental alignments with WebMAUS, and DoReCo's applicability for subsequent research programs. By making the data accessible to the scientific community, DoReCo is designed to bridge the gap between language documentation and linguistic inquiry.},
  langid = {Englisch}
}