Abstract
A large vocabulary continuous speech recognition (LVCSR) system designed for dictation of medieval Latin language documents is introduced. Such language technology tool can be of great help for preserving Latin language charters from this era, as optical character recognition systems are often challenged by these historical materials. As corresponding historical research focuses on the Visegrad region, our primary aim is to make medieval Latin dictation available for texts and speakers of this region, concentrating on Czech, Hungarian and Polish. The baseline acoustic models we start with are monolingual grapheme-based ones. On one hand, the application of medieval Latin knowledge-based grapheme-to-phoneme (G2P) mapping from the source language to the target language resulted in significant improvement, reducing the Word Error Rate (WER) by \(13.3\%\). On the other hand, applying a Unified Simplified Grapheme (USG) inventory set for the three-language acoustic data set complemented with Romanian speech data, resulted in a further \(0.7\%\) WER reduction - without using any target or source language G2P rules.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsNotes
References
Allen, W.S.: Vox Latina: A Guide to the Pronunciation of Classical Latin. Cambridge University Press, Cambridge (1978). [Eng.], 2nd edn., New York
Besacier, L., Barnard, E., Karpov, A., Schultz, T.: Automatic speech recognition for under-resourced languages: a survey. Speech Commun. 56, 85–100 (2014)
Encyclopedia of Caribbean Literature, Latin Regional Pronunciation (2007)
Povey, D., Ghoshal, A., Boulianne, G., Burget, L., Glembek, O., Goel, N., Hannemann, M., Motlicek, P., Qian, Y., Schwarz, P., Silovsky, J., Stemmer, G., Vesely, K.: The Kaldi speech recognition toolkit. In: IEEE 2011 Workshop on Automatic Speech Recognition and Understanding. IEEE Signal Processing Society (2011)
Schultz, T., Waibel, A.: Language-independent and language-adaptive acoustic modeling for speech recognition. Speech Commun. 31, 31–51 (2001)
Stolcke, A.: SRILM - an extensible language modeling toolkit. In: Proceedings of the 7th International Conference on Spoken Language Processing (ICSLP), pp. 901–904 (2002)
Tarjan, B., Mozsolics, T., Balog, A., Halmos, D., Fegyo, T., Mihajlik, P.: Broadcast news transcription in Central-East European languages. In: 3rd IEEE International Conference on Cognitive Infocommunications, pp. 59–64 (2012)
Hungarian speecon database (2003). http://catalog.elra.info/product_info.php?products_id=1093
Czech speecon database (2004). http://catalog.elra.info/product_info.php?products_id=1095
Monasterium.net archive. http://monasterium.net/mom/HU-PBFL/archive
Latin library archive. http://www.thelatinlibrary.com/medieval.html
Waters, A., Bastani, M., Elfeky, M.G., Moreno, P., Velez, X.: Towards acoustic model unification across dialects. In: 2016 IEEE Workshop on Spoken Language Technology (2016)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2017 Springer International Publishing AG
About this paper
Cite this paper
Szabó, L., Mihajlik, P., Balog, A., Fegyó, T. (2017). Unified Simplified Grapheme Acoustic Modeling for Medieval Latin LVCSR. In: Ekštein, K., Matoušek, V. (eds) Text, Speech, and Dialogue. TSD 2017. Lecture Notes in Computer Science(), vol 10415. Springer, Cham. https://doi.org/10.1007/978-3-319-64206-2_47
Download citation
DOI: https://doi.org/10.1007/978-3-319-64206-2_47
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-64205-5
Online ISBN: 978-3-319-64206-2
eBook Packages: Computer ScienceComputer Science (R0)