Abstract
In this paper the use of Hidden Markov Models for the evaluation of the Russian words pronunciation by the foreigners is considered. The average distortion of the codebook and the likelihood of the discrete variable duration Hidden Markov Model are used. Such model allow to take into account the temporary characteristics of a speech signal, which are very important for the evaluation of pronunciation. The results for ten Russian digits are reported.
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.
References
Hiller, S., Rooney, E., Laver, J., Jack, M.: SPELL: SPELL: An Automated System for Computer-Aided Pronunciation Teaching. Speech Communication, 13 (1993).
Kawai, G., Hirose, K.: A CALL System Using Speech Recognition to Train the Pronunciation of Japanese Long Vowels, the Mora Nasal and Mora Obstruents. In Proceedings of EUROSPEECH’97, Greece (1997).
Najmi, A., Bernstein, J.: Speech Recognition in a System for Teaching Japanese. Journal of the Acoustical Society of America, Vol. 100, No. 4 (1996).
Ehsani, F., Bernstein, J., Najmi, A., Todic, O.: SUBARASHI: Japanese Interactive Spoken Language Education. In Proceedings of EUROSPEECH’97, Greece (1997).
Dikareva, S., Kosarev, Y., Machovikov, A., Machovikova, I.: Speech Dialogue in Learning Systems for Foreign Language. In Proceedings of SPECOM’98, St.-Petersburg, Russia (1998).
Ferguson, J.: Variable Duration Models for Speech. In Proceedings of Symposium on Application of Hidden Markov Models to Text and Speech, Princeton (1980).
Kozlov, Yu., Machovikov, A., Maleev, O.: On the Improvements of Speaker-Independent Isolated Word Recognition. In Proceedings of SPECOM’96, St.-Petersburg, Russia (1996).
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 1999 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Machovikov, A., Machovikova, I. (1999). Use of Hidden Markov Models for Evaluation of Russian Digits Pronunciation by the Foreigners. In: Matousek, V., Mautner, P., OcelÃková, J., Sojka, P. (eds) Text, Speech and Dialogue. TSD 1999. Lecture Notes in Computer Science(), vol 1692. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-48239-3_27
Download citation
DOI: https://doi.org/10.1007/3-540-48239-3_27
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-66494-9
Online ISBN: 978-3-540-48239-0
eBook Packages: Springer Book Archive