Abstract
This article deals with a description of a method of accounting of syntactic links in language model for hypotheses obtained after the first passage of decoding of speech. Several stages of processing include POS tagging, dependency parsing, and using factored language models for hypotheses rescoring. The use of fast parsing algorithms such as ‘shift-reduce’ algorithm and rejection of constituency grammar in favor of the dependency grammar allows overcoming the main drawback of the previous approaches, the exponential growth (to the number of lattice nodes) of computations with increase of word lattice size.
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 subscriptionsPreview
Unable to display preview. Download preview PDF.
References
Levenson, S.C.: Mathematical models for speech technology. John Wiley & Sons Ltd., NJ (2005)
Zulkarneev, M.Y., Salman, S.H., Shamraev, N.G.: Use of the Syntactic Information to Increase the Accuracy of Speech Recognition. In: Proceedings of the 14th International Conference on Speech and Computer “SPECOM 2011”, Kazan, pp. 164–166 (2011)
Zulkarneev, M.Y., Shamraev, N.G.: Methods of Rules Generation for Chomsky’s Probabilistic Context-free Grammar in the Problem of Speech Recognition. In: Proceedings of the Science Conference ”Session of the Scientific Council of Russian Academy of Science on Acoustics and XXIV Session of the Russian Acoustical Society”, vol. 3, pp. 21–23. GEOS, Moskow (2012) (in Russian)
Toldova, S.J., Sokolova, E.G., Astaf’eva, I., Gareyshina, A., Koroleva, A., Privoznov, D., Sidorova, E., Tupikina, L., Lyashevskaya, O.N.: NLP Evaluation 2011-2012: Russian syntactic parsers. In: International Conference on Computational Linguistics “Dialog”, Moscow (2012)
Schmid, H.: Probabilistic Part-of-Speech Tagging Using Decision Trees. In: Proceedings of International Conference on New Methods in Language Processing, Manchester, UK (1994)
Nivre, J., Hall, J., Nilsson, J., Chanev, A., Eryiǧit, G., Kubler, S., Marinov, S., Marsi, E.: Malt-Parser: A language-independent system for data-driven dependency parsing. Natural Language Engineering 13(2), 95–135 (2007)
Zulkarneev, M.Y., Shamraev, N.G.: D-gram language model investigation for Russian language modeling. Neirokompiutery: razrabotka, primenenie (Neurocomputers, in Russian). Radiotechnika, Moscow (in press, 2013)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2013 Springer International Publishing Switzerland
About this paper
Cite this paper
Zulkarneev, M., Satunovsky, P., Shamraev, N. (2013). The Use of d-gram Language Models for Speech Recognition in Russian. In: Železný, M., Habernal, I., Ronzhin, A. (eds) Speech and Computer. SPECOM 2013. Lecture Notes in Computer Science(), vol 8113. Springer, Cham. https://doi.org/10.1007/978-3-319-01931-4_48
Download citation
DOI: https://doi.org/10.1007/978-3-319-01931-4_48
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-01930-7
Online ISBN: 978-3-319-01931-4
eBook Packages: Computer ScienceComputer Science (R0)