Abstract
The aim of this paper is to improve speech recognition by enriching language models with automatically detected foreign inclusions from a training text. The enriching is restricted only to foreign, proper-noun inclusions which are typically a dominant part of miss-recognized words. In our suggested approach, character-based n-gram language models are used for detection of foreign, single-word inclusions and for a language identification, and finite state transducers are used to generate foreign pronunciations. Results of this paper show that by enriching language model with English proper nouns found in Czech training text, the recognition of a speech containing English inclusions can be improved by 9.4% relative reduction of WER.
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
Yang, X., Liang, W.: An N-Gram-and-Wikipedia joint approach to Natural Language Identification. In: 2010 4th International Universal Communication Symposium (IUCS), pp. 332–339 (2010)
Martins, B., Silva, M.J.: Language identification in web pages. In: Proceedings of the 2005 ACM Symposium on Applied Computing, SAC 2005, pp. 764–768. ACM, New York (2005)
Zissman, M.A., Singer, E.: Automatic language identification of telephone speech messages using phoneme recognition and n-gram modeling. In: 1994 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 1994, vol. 1, pp. I/305–I/308 (1994)
Zissman, M.A.: Language identification using phoneme recognition and phonotactic language modeling. In: 1995 International Conference on Acoustics, Speech, and Signal Processing, ICASSP 1995, vol. 5, pp. 3503–3506 (1995)
Yan, E.Y., Barnard: An approach to automatic language identification based on language-dependent phone recognition. In: 1995 International Conference on Acoustics, Speech, and Signal Processing, ICASSP 1995, vol. 5, pp. 3511–3514 (1995)
Matejka, P., Schwarz, P., Cernocký, J., Chytil, P.: Phonotactic language identification using high quality phoneme recognition. In: INTERSPEECH, pp. 2237–2240 (2005)
Ahmed, B., Cha, S.H., Tappert, C.: Detection of Foreign Entities in Native Text Using N-gram Based Cumulative Frequency Addition. In: Proceedings of CSIS Research Day. Pace University, New York (2005)
Hakkinen, J., Tian, J.: N-gram and decision tree based language identification for written words. In: IEEE Workshop on Automatic Speech Recognition and Understanding, ASRU 2001, pp. 335–338 (2001)
Maison, B., Chen, S., Cohen, P.S.: Pronunciation modeling for names of foreign origin. In: 2003 IEEE Workshop on Automatic Speech Recognition and Understanding, ASRU 2003, pp. 429–434 (2003)
Stolcke, A.: Srilm-an extensible language modeling toolkit. In: Proceedings International Conference on Spoken Language Processing, pp. 257–286 (November 2002)
Project Gutenberg, http://www.gutenberg.org
Novak, J., Dixon, P.: Improving WFST-based G2P conversion with alignment constraints and RNNLM N-best rescoring. In: Proceedings of International Conference on Spoken Language Processing Interspeech 2012 (2012)
Švec, J., Hoidekr, J., Soutner, D., Vavruška, J.: Web text data mining for building large scale language modelling corpus. In: Habernal, I., Matoušek, V. (eds.) TSD 2011. LNCS, vol. 6836, pp. 356–363. Springer, Heidelberg (2011)
Skorkovská, L., Ircing, P., Pražák, A., Lehečka, J.: Automatic Topic Identification for Large Scale Language Modeling Data Filtering. In: Habernal, I., Matoušek, V. (eds.) TSD 2011. LNCS, vol. 6836, pp. 64–71. Springer, Heidelberg (2011)
The CMU Pronouncing Dictionary, http://www.speech.cs.cmu.edu/cgi-bin/cmudict
Pražák, A., Loose, Z., Trmal, J., Psutka, J.V., Psutka, J.: Captioning of live TV programs through speech recognition and re-speaking. In: Sojka, P., Horák, A., Kopeček, I., Pala, K. (eds.) TSD 2012. LNCS, vol. 7499, pp. 513–519. Springer, Heidelberg (2012)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2013 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Lehečka, J., Švec, J. (2013). Improving Speech Recognition by Detecting Foreign Inclusions and Generating Pronunciations. In: Habernal, I., Matoušek, V. (eds) Text, Speech, and Dialogue. TSD 2013. Lecture Notes in Computer Science(), vol 8082. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-40585-3_38
Download citation
DOI: https://doi.org/10.1007/978-3-642-40585-3_38
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-40584-6
Online ISBN: 978-3-642-40585-3
eBook Packages: Computer ScienceComputer Science (R0)