Language Identification for Under-Resourced Languages in the Basque Context

  • Nora Barroso
  • Karmele López de Ipiña
  • Manuel Graña
  • Aitzol Ezeiza
Conference paper
Part of the Advances in Intelligent and Soft Computing book series (AINSC, volume 87)

Abstract

Automatic Speech Recognition (ASR) is a broad research area that absorbs many efforts from the research community. The interest on Multilingual Systems arouses in the Basque Country because there are three official languages (Basque, Spanish, and French), and there is much linguistic interaction among them, even if Basque has very different roots than the other two languages. The development of Multilingual Large Vocabulary Continuous Speech Recognition systems involves issues as: Language Identification, Acoustic Phonetic Decoding, Language Modeling or the development of appropriate Language Resources. This paper describes the development of a Language Identification (LID) system oriented to robust Multilingual Speech Recognition in the Basque context. The work presents hybrid strategies for LID, based on the selection of system elements by several classifiers and Discriminant Analysis improved with robust regularized covariance matrix estimation methods oriented to under-resourced languages and stochastic methods for speech recognition tasks (Hidden Markov Models and n-grams).

Keywords

Language Identification Under Resourced Languages Discriminant Analysis Covariance Matrix Estimation Methods 
This is a preview of subscription content, log in to check access.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Schultz, T., Kirchhoff, N.: Multilingual Speech Processing. Elsevier, Amsterdam (2006)Google Scholar
  2. 2.
    Schultz, T., Waibel, A.: Multilingual and Crosslingual Speech Recognition. In: Proceedings of the DARPA Broadcast News. Workshop (1998)Google Scholar
  3. 3.
    Le, V.B., Besacier, L.: Automatic speech recognition for under-resourced languages: application to Vietnamese language. IEEE Transactions on Audio, Speech, and Language Processing 17(8), 1471–1482 (2009)CrossRefGoogle Scholar
  4. 4.
    Seng, S., Sam, S., Le, V.B., Bigi, B., Besacier, L.: Which Units For Acoustic and Language Mod-eling For Khmer Automatic Speech Recognition. In: 1st International Conference on Spoken Language Processing for Under-resourced languages Hanoi, Vietnam (2008)Google Scholar
  5. 5.
    Lyu, D.-C., Lyu, R.-Y.: Language Identification on Code-Switching Utterances Using Multiple Cues. In: Proc of Interspeech (2008)Google Scholar
  6. 6.
    Lopez de Ipiña, K., Graña, M., Ezeiza, N., Hernández, M., Zulueta, E., Ezeiza, A., Tovar, C.: Selection of Lexical Units for Continuous Speech Recognition of Basque. In: Sanfeliu, A., Ruiz-Shulcloper, J. (eds.) CIARP 2003. LNCS, vol. 2905, pp. 244–250. Springer, Heidelberg (2003)CrossRefGoogle Scholar
  7. 7.
    Barroso, N., Ezeiza, A., Gilisagasti, N., Lopez de Ipiña, K., López, A., López, J.M.: Development of Multimodal Resources for Multilingual Information Retrieval in the Basque context. In: Proccedings of Interspeech 2007, Antwerp, Belgium (2007)Google Scholar
  8. 8.
    Li, H., Ma, B.: A Phonotactic Language Model for Spoken LID. In: ACL 2005 (2005)Google Scholar
  9. 9.
    Ma, B., Li, H.: An Acoustic Segment Modeling Approach to Automatic Language Identification. In: Proc. Interspeech 2005, Lisbon, Portugal, pp. 2829–2832 (2005)Google Scholar
  10. 10.
    Matejka, P., Schwarz, P., Cernocky, J., Chytil, P.: Phonotactic LID using High Quality Phoneme Recognition. In: Proc. Interspeech 2005, Lisbon, Portugal, pp. 2237–2240 (2005)Google Scholar
  11. 11.
    Nagarajan, T., Murthy, H.A.: Language Identification, Using Parallel Syllable-Like Unit Recognition. In: Proc ICASSP 2004, pp. 401–404 (2004)Google Scholar
  12. 12.
    Vandecatseye, A., Martens, J.P., Neto, J., Meinedo, H., Garcia-Mateo, C., Dieguez, F.J., Mihelic, F., Zibert, J., Nouza, J., David, P., Pleva, M., Cizmar, A., Papageorgiou, H., Alexandris, C.: The COST278 pan-European Broadcast News Database. In: Proceedings of LREC 2004, Lisbon, Portugal (2004)Google Scholar
  13. 13.
    Wheatley, B., Kondo, K., Anderson, W., Muthusamy, Y.: An evaluation of Cross-Language Adaptation for Rapid HMM Development in a New Language. In: International Conference on Acoustics, Speech, and Signal Processing, Adelaine, pp. 237–240 (1994)Google Scholar
  14. 14.
    Toledano, D., Moreno, A., Colás, J., Garrido, J.: Acoustic-phonetic decoding of different types of spontaneous speech in Spanish. In: Disfluencies in Spontaneous Speech 2005, Aix-en-Provence, France (2005)Google Scholar
  15. 15.
    Padrell, J., Martín-Iglesias, D., Díaz-de-María, F.: Support Vector Machines for Continuous Speech Recognition. In: 14th European Signal Processing Conference (BSSIPCO 2006), Florence, Italy, September 4-8 (2006)Google Scholar
  16. 16.
    Ganapathiraju, A., Hmaker, J., Picone, J.: Hybrid SVM/HMM architectures for speech recognition. In: Proc. of the International Conference on Spoken Language Processing, vol. 4, pp. 504–507 (2000)Google Scholar
  17. 17.
    Smith, N., Gales, M.: Speech recognition using SVMs. In: Advances in Neural Information Processing Systems, vol. 14. MIT Press, Cambridge (2002)Google Scholar
  18. 18.
    Cosi, P.: Hybrid HMM-NN architectures for connected digit recognition. In: Proc. of the International Joint Conference on Neural Networks, vol. 5 (2000)Google Scholar
  19. 19.
    Friedman, J.H.: Regularized discriminant analysis. Journal of the American Statistical Association 84, 165–175 (1989)MathSciNetCrossRefGoogle Scholar
  20. 20.
    Martinez, A., Kak, A.: PCA versus LDA. IEEE Transactions on Pattern Analysis and Machine Intelligence 23(2), 228–233 (2001)CrossRefGoogle Scholar
  21. 21.
    Hoffbeck, J.P., Landgrebe, D.: Covariance estimation and classification with limited training data. IEEE Transactions on Pattern Analysis and Machine Intelligence 18(7), 763–767 (1996)CrossRefGoogle Scholar
  22. 22.
    Tadjudin, S., Landgrebe, D.: Classification of high dimensional data with limited training samples. Technical Report TRECE 98-8. School of Electrical and Computer Engineering, Purdue University, West Lafayette, Indiana (1998)Google Scholar
  23. 23.
    Tadjudin, S., Landgrebe, D.: Covariance Estimation with Limited Training Samples. IEEE Transaction on Geoscience and Remote Sensing 37 (2000); Appendix: Springer-Author DiscountGoogle Scholar
  24. 24.
    Ambikairajah, L., Choi, E.: Robust language identification based on fused phonotactic information with MLKSFM ICME. In: IEEE International Conference on pre-classifier, Multimedia and Expo. (2005)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2011

Authors and Affiliations

  • Nora Barroso
    • 1
  • Karmele López de Ipiña
    • 2
  • Manuel Graña
    • 2
  • Aitzol Ezeiza
    • 2
  1. 1.Irunweb EnterpriseIrunBasque Country
  2. 2.Grupo de Inteligencia ComputacionalUPV/EHUSpain

Personalised recommendations