@incollection{Brinckmann2017,
  author    = {Caren Brinckmann},
  title     = {Transcription Bottleneck of Speech Corpus Exploitation},
  series = {Proceedings of the Second Colloquium on Lesser Used Languages and Computer Linguistics (LULCL II). \"Combining efforts to foster computational support of minority languages\"},
  editor    = {Verena Lyding},
  publisher = {Europ{\"a}ische Akademie},
  address   = {Bozen},
  isbn      = {978-88-88906-52-2},
  url       = {https://nbn-resolving.org/urn:nbn:de:bsz:mh39-68329},
  pages     = {165 -- 179},
  year      = {2017},
  abstract  = {While written corpora can be exploited without any linguistic annotations, speech corpora need at least a basic transcription to be of any use for linguistic research. The basic annotation of speech data usually consists of time-aligned orthographic transcriptions. To answer phonetic or phonological research questions, phonetic transcriptions are needed as well. However, manual annotation is very time-consuming and requires considerable skill and near-native competence. Therefore it can take years of speech corpus compilation and annotation before any analyses can be carried out. In this paper, approaches that address the transcription bottleneck of speech corpus exploitation are presented and discussed, including crowdsourcing the orthographic transcription, automatic phonetic alignment, and query-driven annotation. Currently, query-driven annotation and automatic phonetic alignment are being combined and applied in two speech research projects at the Institut f{\"u}r Deutsche Sprache (IDS), whereas crowdsourcing the orthographic transcription still awaits implementation.},
  language  = {en}
}