Communications - Scientific Letters of the University of Zilina 2010, 12(1):58-64 | DOI: 10.26552/com.C.2010.1.58-64

Clustering of Slovak Sentence Melody - Methods and Results

Maria Cernanska1, Ondrej Skvarek1
1 Department of Information Networks, Faculty of Management and Informatics, University of Zilina, Slovakia

Modern speech synthesis systems implement prosody features to achieve more naturally sounding voices, trying to produce sounds similar to the human speech. This article deals with obtaining one of prosody characteristics (sentence melody contour) from human speech recordings. Similarities of melody contours are studied using cluster analysis. Several clustering methods are evaluated for this purpose, estimation of proper number of clusters is described and typical melodies for different types of Slovak language sentences (declarative, interrogative, exclamatory, clauses with final "," etc.) are found and recommended for implementation in our text-to-speech system.

Keywords: speech synthesis, prosody, melody contour, cluster analysis, R-software

Published: March 31, 2010  Show citation

ACS AIP APA ASA Harvard Chicago Chicago Notes IEEE ISO690 MLA NLM Turabian Vancouver
Cernanska, M., & Skvarek, O. (2010). Clustering of Slovak Sentence Melody - Methods and Results. Communications - Scientific Letters of the University of Zilina, 12(1), 58-64. doi: 10.26552/com.C.2010.1.58-64
Share...
Download citation
  • BibTeX (.bib)
  • Bookends (.ris)
  • EasyBib (.ris)
  • EndNote (.enw)
  • EndNote 8 (.xml)
  • ISI WoS (.isi)
  • Medlars (.medlars)
  • Mendeley (.ris)
  • MODS (.xml)
  • Papers (.ris)
  • RefWorks (.txt)
  • RefManager (.ris)
  • RIS (.ris)
  • MS Word (.xml)
  • Zotero (.ris)
    • Open full article

    References

    1. ANDERBERG, M. R.: Cluster Analysis for Applications, Academic Press, New York, 1973.
    2. BOERSMA, P.: Accurate Short-term Analysis of the Fundamental Frequency and the Harmonics-to-noise Ratio of a Sampled Sound, Inst. of Phonetic Sciences 17, 97-110. Univ. of Amsterdam, 1993.
    3. CAKY P., KLIMO, M., MIHALIK, I., MLADSIK, R.: Text-to-speech for Slovak Language, In proc. of the 7th international conference Text, speech and dialogue, TSD 2004, Brno - Berlin: Springer, 2004. Go to original source...
    4. CERNANSKA, M., SKVAREK, O.: Sentence Melody Analysis for Speech Production in the TTS system. In proc. of the TRANSCOM 2009: 8th European conference of young research and scientific workers, University of Zilina, 2009, Section 3: Information and communication technologies, p. 25-30.
    5. DOWNS, G. M., BARNARD, J. M.: Hierarchical and non-Hierarchical Clustering. Poster presented at Daylight EUROMUG meeting. GlaxoWellcome, Stevenage, 1995. BCI Barnard Chemical Information Ltd. Sheffield S6 6BX.
    6. KOWALSKI, G.: Information Retrieval Systems, Theory and Implementation, Kluver Academic Publishers, 1999.
    7. KRAL, A.: The Pronunciation Rules of Slovak (in Slovak), Systematika a ortoepicky slovnik, Neografia, Martin 2005.
    8. MELOUN, M., MILITKY, J.: Statistical Analysis of Experimental Data (in Czech), ACADEMIA, 2004
    9. MURTAGH, F.: Correspondence Analysis and Data Coding with R and Java, Chapman and Hall/CRC Press, 2005. Go to original source...
    10. TTS system version 1 demo, http://tts.kis.fri.utc.sk (taken: August 23 2009)
    11. Program Praat main web page, http://www.fon.hum.uva.nl/praat (taken: August-23 2009.)
    12. The R Project for Statistical Computing, http://www.r-project.org/
    13. Electronic Textbook StatSoft, http://statsoft.com/textbook (taken: August-18 2009)
    14. XU, R., WUNSCH, D. Clustering. Wiley-IEEE Press, 2009. Go to original source...
    15. CERNANSKA, M., SKVAREK, O.: Clustering Methods used to Obtain Typical Sentence Melody Contours for Slovak Language TTS system. Accepted at the conference: The Second International Scientific Conference on Applied Natural Sciences, 2009, Trnava
    16. KELEOVA, VASILKOVA, T. Cukor a sol. Ikar, Bratislava, 2004. (novel written in Slovak language)

    This is an open access article distributed under the terms of the Creative Commons Attribution 4.0 International License (CC BY 4.0), which permits use, distribution, and reproduction in any medium, provided the original publication is properly cited. No use, distribution or reproduction is permitted which does not comply with these terms.


    Return to the content