Abstract
We report on a series of experiments addressing the fact that German is less suited than English for word-based n-gram language models. Several systems were trained at different vocabulary sizes using various sets of lexical units. They were evaluated against a newly created corpus of German and Austrian broadcast news.
This is a preview of subscription content, log in via an institution to check access.
Preview
Unable to display preview. Download preview PDF.
References
Stedje, A.: Deutsche Sprache gestern und heute. UTB für Wissenschaft, München (1999).
Adda-Decker, M., Adda, G., Lamel, L.: Investigating Text Normalization and Pronunciation Variants for German Broadcast Transcription. Proceedings of the 6th International Conference of Spoken Language Processing, ICSLP 2000 (Beijing, China).
Larson, M., Willett, D., Köhler, J., Rigoll, G.: Compound Splitting and Lexical Unit Recombination for Improved Performance of a Speech Recognition System for German Parliamentary Speeches. Proceedings of the 6th International Conference of Spoken Language Processing, ICSLP 2000 (Beijing, China).
Berton, A., P. Fetter, P., Regel-Brietzmann, P.: Compound Words in Large-Vocabulary German Speech Recognition Systems. Proceedings of the 4th International Conference of Spoken Language Processing, ICSLP 1996 (Philadelphia, Pennsylvania, USA).
Barras, C., Geoffrois, E., Wu, Z., M. Liberman, M.: Transcriber: Free Tool for Segmenting, Labeling and Transcribing Speech. Proceedings of the 1st International Conference on LREC (1998).
Kubala, F., Jin, H., Nguyen, L., Schwartz, R., Matsoukas, S.: Broadcast News Transcription. Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 1997 (Munich, Germany).
Nguyen, L., Matsoukas, S., Davenport, J., Liu, D., Billa, J., Kubala, F., Makhoul, J.: Further Advances in Transcription of Broadcast News. Proceedings of the 6th European Conference on Speech Communication and Technology, EuroSpeech 1999 (Budapest, Hungary).
Colthurst, T., Kimball, O., Richurdson, F., Han, S., Wooters, C., Iyer, R., Gish, H.: The 2000 BBN Byblos LVCSR System. Proceedings of the 6th International Conference of Spoken Language Processing, ICSLP 2000 (Beijing, China).
Kemp, T., Geutner, P., Schmidt, M., Tomaz, B., Weber, M., Westphal, M., Waibel, A.: The Interactive Systems Labs View4You Video Indexing System. Proceedings of the 5th International Conference of Spoken Language Processing, ICSLP’98 (Sydney, Australia).
Backfried, G., Hecht, R., Loots, S., Pfannerer, N., Riedler, J., Schiefer, C.: Creating a European English Broadcast News Transcription Corpus and System. Proceedings of the 7th European Conference on Speech Communication and Technology, EuroSpeech 2001 (Aalborg, Denmark).
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2002 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Hecht, R., Riedler, J., Backfried, G. (2002). Fitting German into N-Gram Language Models. In: Sojka, P., Kopeček, I., Pala, K. (eds) Text, Speech and Dialogue. TSD 2002. Lecture Notes in Computer Science(), vol 2448. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-46154-X_49
Download citation
DOI: https://doi.org/10.1007/3-540-46154-X_49
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-44129-8
Online ISBN: 978-3-540-46154-8
eBook Packages: Springer Book Archive