Abstract
This paper describes development of a large vocabulary continuous speaker independent speech recognition system for Estonian. Estonian is an agglutinative language and the number of different word forms is very large, in addition, the word order is relatively unconstrained. To achieve a good language coverage, we use pseudo-morphemes as basic units in a statistical trigram language model. To improve language model robustness, we automatically find morpheme classes and interpolate the morpheme model with the class-based model. The language model is trained on a newspaper corpus of 15 million word forms. Clustered triphones with multiple Gaussian mixture components are used for acoustic modeling. The system with interpolated morpheme language model is found to perform significantly better than the baseline word form trigram system in all areas. The word error rate of the best system is 27.7% which is a 10.0% absolute improvement over the baseline system.
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
Preview
Unable to display preview. Download preview PDF.
Similar content being viewed by others
References
Waibel, A., Geutner, P., Tomokiyo, L., Schultz, T., Woszczyna, M.: Multilinguality in speech and spoken language systems. Proceedings of the IEEE 88, 1297–1313 (2000)
Kwon, O.W., Park, J.: Korean large vocabulary continuous speech recognition with morphemebased recognition units. Speech Communication 39, 287–300 (2003)
Szarvas, M., Furui, S.: Evaluation of the stochastic morphosyntactic language model on a one million word Hungarian dictation task. In: Proceedings of EuroSpeech 2003, Geneva (2003)
Siivola, V., Hirsimäki, T., Creutz, M., Kurimo, M.: Unlimited vocabulary speech recognition based on morphs discovered in an unsupervised manner. In: Proceedings of EuroSpeech 2003, Geneva (2003)
Eek, A., Meister, E.: Estonian speech in the BABEL multi-language database: Phoneticphonological problems revealed in the text corpus. In: Proceedings of LP 1998, vol. II, pp. 529–546 (1999)
Hennoste, T., Kaalep, H.J., Muischnek, K., Paldre, L., Vaino, T.: The Tartu University corpus of Estonian literary language. In: Abstracts. Congressus nonus internationalis fenno-ugristarum. Pars II, Tartu, pp. 338–339 (2000)
Young, S., Evermann, G., Kershaw, D., Moore, G., Odell, J., Ollason, D., Povey, D., Valtchev, V., Woodland, P.: The HTK Book (for HTK Version 3.2) (2003), http://htk.eng.cam.ac.uk
Kneser, R., Ney, H.: Improved clustering techniques for class-based statistical language modelling. In: Proceedings of the European Conference on Speech Communication and Technology, pp. 973–976 (1993)
Lee, A., Kawahara, T., Shikano, K.: Julius—an open source real-time large vocabulary recognition engine. In: Proceedings of the European Conference on Speech Communication and Technology (EuroSpeech), pp. 1691–1694 (2001)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2004 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Alumäe, T. (2004). Large Vocabulary Continuous Speech Recognition for Estonian Using Morphemes and Classes. In: Sojka, P., Kopeček, I., Pala, K. (eds) Text, Speech and Dialogue. TSD 2004. Lecture Notes in Computer Science(), vol 3206. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-30120-2_31
Download citation
DOI: https://doi.org/10.1007/978-3-540-30120-2_31
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-23049-6
Online ISBN: 978-3-540-30120-2
eBook Packages: Springer Book Archive