Abstract
In this research, we contribute to the preservation of dialects by producing a searchable parallel audio corpus. We constructed a parallel spoken corpus for dialects in middle west Germany with a web-based search interface in order to look up the database of the spoken documents. The audio documents are initially collected as part of the DMW (Dialektatlas Mittleres Westdeutschland) project for showing which dialectal or dialect-related varieties currently exist in Central West Germany and describes them in their important characteristics. Selected people in particular places in the region are interviewed to answer a list of questions prepared by linguists. The collected data are systematically processed, analyzed and documented on a phonetic-phonological, morphological, syntactic and lexical level. Thus, this research utilizes these processed audio data and the corresponding standard German text to create a parallel spoken corpus of dialects in middle west Germany and standard German. Finally, we created a web-based search interface that accepts standard German text and returns its translation into the nine dialects.
As a result, we created a parallel spoken corpus for nine dialects, each having a parallel audio data of size 550 for each dialect, where size is measured by the count of words or phrases. The outcome of this work could be used in computer-supported language learning, language variety identification as well as speech recognition.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
- 2.
Informant is a person who is interviewed.
- 3.
References
Aynalem, T.M., Sabine, R.: Towards Parallel corpora construction: standard German –Plattdeutsch. In: Parallel Corpora: Creation and Applications International Symposium PaCor, Madrid (2018)
Barbiers, S., Leonie, C., Kunst, J.P.: The Syntactic Atlas of the Dutch Dialects (SAND): a corpus of elicited speech and text as an online dynamic atlas. In: Creating and Digitizing Language Corpora, pp. 54–90, Palgrave Macmillan, London (2007)
Bernard, H.R.: Preserving language diversity. Human Organization 51(1), 82–89 (1996). In: Indigenous Literacies in the Americas: Language Planning from the Bottom up. ed. by Hornberger, N.H., pp. 139-156. Mouton de Gruyter, Berlin (1992)
Castelruiz, A., Sánchez, J., Zalbide, X., Navas, E., Graminde. I.: Description and design of a web accessible multimedia archive. In: Proceedings of the 12th IEEE Mediterranean Electrotechnical Conference (IEEE Cat. No. 04 CH37521), Vol. 2, pp. 681–684. IEEE (2004)
Chang-Castillo and Associates. https://ccalanguagesolutions.com/language-preservation-how-countries-preserve-their-languages/. Accessed 1 Oct 2019
Koneva, E.V., Gural, S.K.: The role of dialects in German society. In: The XXVI Annual International Academic Conference, Language and Culture, pp. 248–252 (2015)
Karasimos, A., Melissaropoulou, D., Papazachariou, D., Assimakopoulos, D.: GreeD: cataloguing and encoding modern greek dialectal oral corpora. In: Proceedings of CatCod, Orleans, France (2008)
Lothian, D., Akcayir, G., Carrie, D.E.: Accommodating Indigenous People When Using Technology to Learn Their Ancestral Language. At Edmonton, Alberta (2019)
Moseley, C., (ed.): Atlas of the World’s Languages in Danger, 3rd edn. UNESCO Publishing, Paris (2010). http://www.unesco.org/culture/en/endangeredlanguages/atlas. Accessed 01 Oct 2016
UNESCO: Language Vitality and Endangerment Ad Hoc Expert Group on Endangered Languages, International Expert Meeting on UNESCO Programme Safeguarding of Endangered Languages (2003)
Acknowledgement
We would like to acknowledge the informants who have participated in the recordings and linguistic experts in the DMW project who have worked on audio processing.
linguistic experts in the DMW project who have worked on audio processing.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this paper
Cite this paper
Misganaw, A.T., Roller, S. (2020). PlattForm: Parallel Spoken Corpus of Middle West German Dialects with Web-Based Interface. In: Nicosia, G., et al. Machine Learning, Optimization, and Data Science. LOD 2020. Lecture Notes in Computer Science(), vol 12566. Springer, Cham. https://doi.org/10.1007/978-3-030-64580-9_41
Download citation
DOI: https://doi.org/10.1007/978-3-030-64580-9_41
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-64579-3
Online ISBN: 978-3-030-64580-9
eBook Packages: Computer ScienceComputer Science (R0)