Syllable-Based Recognition Unit to Reduce Error Rate for Korean Phones, Syllables and Characters

  • Bong-Wan Kim
  • Yongnam Um
  • Yong-Ju Lee
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4188)


In this paper we propose a new type of syllable-based unit for recognition and language model to improve recognition rate for Korean phones, syllables and characters. We propose ‘combined’ units for which both Korean characters and syllable units realized in speech are taken into consideration. We can obtain character, syllable and phone sequences directly from the recognition results by using proposed units. To test the performance of the proposed approach we perform two types of experiments. First, we perform language modeling for phones, characters, syllables and propose combined units based on the same text corpus, and we test the performance for each unit. Second, we perform a vector space model based retrieval experiment by using the proposed combined units.


Acoustic Model Text Corpus Reduce Error Rate Recognition Unit Combine Unit 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Ng, K.: Subword-based Approaches for Spoken Document Retrieval, Ph.D. Thesis, Massachusetts Institute of Technology (MIT), Cambridge, MA (2000)Google Scholar
  2. 2.
    Moreau, N., Kim, H.-G., Sikora, T.: Phone-based Spoken Document Retrieval in Conformance with the MPEG-7 Standard. In: 25th International AES Conference (Metadata for Audio), London, UK (2004)Google Scholar
  3. 3.
    Speech/Language Technology Research Department in ETRI,
  4. 4.
    SiTEC (Speech Information Technology and Industry Promotion Center),
  5. 5.
    Sohn, H.-M.: The Korean language. Cambridge University Press, Cambridge (1999)Google Scholar
  6. 6.
    Korea Broadcasting System, Dictionary of Standard Pronunciation of Korean, Emunkak (1993)Google Scholar
  7. 7.
    HTK (Hidden Markov Model Toolkit),
  8. 8.
    CMU-Cambridge Statistical Language Modeling toolkit,
  9. 9.
    Salton, G., McGill, M.J.: Introduction to Modern Information Retrieval. McGraw-Hill, New York (1983)MATHGoogle Scholar
  10. 10.
    TREC, Common Evaluation Measures, NIST. In: 10th Text Retrieval Conference (TREC 2001), Gaithersburg, MD (2001)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Bong-Wan Kim
    • 1
  • Yongnam Um
    • 1
  • Yong-Ju Lee
    • 2
  1. 1.Speech Information Technology and Industry Promotion CenterWonkwang UniversityKorea
  2. 2.Division of Electrical Electronic and Information EngineeringWonkwang UniversityKorea

Personalised recommendations