@inproceedings{Schmidt2014, author = {Schmidt, Thomas}, title = {The database for spoken German - DGD2}, booktitle = {Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC'14)}, url = {http://www.lrec-conf.org/proceedings/lrec2014/summaries/171.html}, pages = {1451 -- 1457}, year = {2014}, abstract = {The Database for Spoken German (Datenbank f{\"u}r Gesprochenes Deutsch, DGD2, http://dgd.ids-mannheim.de) is the central platform for publishing and disseminating spoken language corpora from the Archive of Spoken German (Archiv f{\"u}r Gesprochenes Deutsch, AGD, http://agd.ids-mannheim.de) at the Institute for the German Language in Mannheim. The corpora contained in the DGD2 come from a variety of sources, some of them in-house projects, some of them external projects. Most of the corpora were originally intended either for research into the (dialectal) variation of German or for studies in conversation analysis and related fields. The AGD has taken over the task of permanently archiving these resources and making them available for reuse to the research community. To date, the DGD2 offers access to 19 different corpora, totalling around 9000 speech events, 2500 hours of audio recordings or 8 million transcribed words. This paper gives an overview of the data made available via the DGD2, of the technical basis for its implementation, and of the most important functionalities it offers. The paper concludes with information about the users of the database and future plans for its development.}, subject = {gesprochene Sprache}, language = {en} }