@inproceedings{FauthBonneauZimmereretal.2017,
  author    = {Camille Fauth and Anne Bonneau and Frank Zimmerer and J{\"u}rgen Trouvain and Bistra Andreeva and Vincent Colotte and Dominique Fohr and Denis Jouvet and Jeanin J{\"u}gler and Yves Laprie and Odile Mella and Bernd M{\"o}bius},
  title     = {Designing a Bilingual Speech Corpus for French and German Language Learners: a Two-Step Process},
  series = {Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC'14). May 26-31, 2014. Harpa Concert Hall and Conference Center. Reykjavik, Iceland},
  editor    = {Nicoletta Calzolari and Khalid Choukri and Thierry Declerck and Hrafn Loftsson and Bente Maegaard and Joseph Mariani and Asuncion Moreno and Jan Odijk and Stelios Piperidis},
  publisher = {European Language Resources Association},
  address   = {Paris},
  isbn      = {978-2-9517408-8-4},
  url       = {https://nbn-resolving.org/urn:nbn:de:bsz:mh39-59154},
  pages     = {1477 -- 1482},
  year      = {2017},
  abstract  = {We present the design of a corpus of native and non-native speech for the language pair French-German, with a special emphasis on phonetic and prosodic aspects. To our knowledge there is no suitable corpus, in terms of size and coverage, currently available for the target language pair. To select the target L1-L2 interference phenomena we prepare a small preliminary corpus (corpus1), which is analyzed for coverage and cross-checked jointly by French and German experts. Based on this analysis, target phenomena on the phonetic and phonological level are selected on the basis of the expected degree of deviation from the native performance and the frequency of occurrence. 14 speakers performed both L2 (either French or German) and L1 material (either German or French). This allowed us to test, recordings duration, recordings material, the performance of our automatic aligner software. Then, we built corpus2 taking into account what we learned about corpus1. The aims are the same but we adapted speech material to avoid too long recording sessions. 100 speakers will be recorded. The corpus (corpus1 and corpus2) will be prepared as a searchable database, available for the scientific community after completion of the project.},
  language  = {en}
}