Skip to main content
SpringerLink
Log in
Book cover

International Conference on Text, Speech and Dialogue

TSD 2004: Text, Speech and Dialogue pp 147–153Cite as

Automatic Language Identification Using Phoneme and Automatically Derived Unit Strings

  • Conference paper

  • 863 Accesses

Part of the book series: Lecture Notes in Computer Science ((LNAI,volume 3206))

Abstract

Language identification (LID) based on phonotactic modeling is presented in this paper. Approaches using phoneme strings and strings of units automatically derived by an Ergodic HMM (EHMM) are compared. The phoneme recognizers were trained on 6 languages from OGI multi-language-corpus and Czech SpeechDat-E. The LID results are obtained on 4 languages. The results show superiority of Czech phoneme recognizer while used in LID and promising trends using the EHMM-derived units.

This is a preview of subscription content, log in via an institution.

Chapter
USD   29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD   84.99
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD   109.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Learn about institutional subscriptions

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. Schwarz, P., Matějka, P., Cěrnocký, J.: Recognition of Phoneme Strings using TRAP Technique. In: Proc. EuroSpeech 2003, September 2003, pp. 825–828 (2003)

    Google Scholar 

  2. Sharma, S., Ellis, D., Karajekar, S., Jain, P., Hermansky, H.: Feature extraction using non-linear transformation for robust speech recognition on the Aurora database. In: Proc. ICASSP 2000, Turkey (2000)

    Google Scholar 

  3. Hermansky, H., Sharma, S.: Temporal Patterns (TRAPS) in ASR of Noisy Speech. In: Proc. ICASSP 1999, Phoenix, Arizona, USA (March 1999)

    Google Scholar 

  4. Schwarz, P., Matějka, P., Černocký, J.: Towards Lower Error Rates in Phoneme Recognition. In: Sojka, P., et al. (eds.) Text, Speech and Dialogue, Proceedings of the Seventh International Conference, Brno, Czech Republic, September 8-11, p. 221 (2004)

    Google Scholar 

  5. Szöke, I., Cěrnocký, J.: Speech Units Automatically Generated by Ergodic Hidden Markov Model. Submitted to EEICT (2004)

    Google Scholar 

  6. Cěrnocký, J., Baudoin, G., Chollet, G.: Segmental vocoder - going beyond the phonetic approach. In: Proc. IEEE ICASSP 1998, May 1998, pp. 605–608 (1998)

    Google Scholar 

  7. The SPRACHcore software packages, http://www.icsi.berkeley.edu/~dpwe/projects/sprach

  8. HTK toolkit, http://htk.eng.cam.ac.uk

  9. OGI MultiLanguage Telephone Speech (January 2004), http://www.cslu.ogi.edu/corpora/mlts/

Download references

Author information

Authors and Affiliations

  1. Faculty of Elec. Eng. and Communication, Brno University of Technology,  

    Pavel Matějka

  2. Faculty of Information Technology, Brno University of Technology,  

    Pavel Matějka, Igor Szöke, Petr Schwarz & Jan Černocký

  3. ESIEE Paris, Dpt. Signal et Télécommunications,  

    Igor Szöke

Authors
  1. Pavel Matějka
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Igor Szöke
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Petr Schwarz
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Jan Černocký
    View author publications

    You can also search for this author in PubMed Google Scholar

Editor information

Editors and Affiliations

  1. Faculty of Informatics, Masaryk University, Brno, Czech Republic

    Petr Sojka

  2. Faculty of Informatics, Masaryk University, Botanická 68a, CZ-602 00, Brno, Czech Republic

    Ivan Kopeček

  3. Faculty of Informatics, Department of Computer Graphics and Design, Masaryk University, Botanická 68a, 602 00, Brno, Czech Republic

    Karel Pala

Rights and permissions

Reprints and permissions

Copyright information

© 2004 Springer-Verlag Berlin Heidelberg

About this paper

Cite this paper

Matějka, P., Szöke, I., Schwarz, P., Černocký, J. (2004). Automatic Language Identification Using Phoneme and Automatically Derived Unit Strings. 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_19

Download citation

  • DOI: https://doi.org/10.1007/978-3-540-30120-2_19

  • Publisher Name: Springer, Berlin, Heidelberg

  • Print ISBN: 978-3-540-23049-6

  • Online ISBN: 978-3-540-30120-2

  • eBook Packages: Springer Book Archive

Publish with us

Policies and ethics

Search

Navigation