Integrating Contrast in a Framework for Predicting Prosody

  • Pepi Stavropoulou
  • Dimitris Spiliotopoulos
  • Georgios Kouroupetroglou
Part of the Lecture Notes in Computer Science book series (LNCS, volume 6008)


Information Structure (IS) is known to bear a significant effect on Prosody, making the identification of this effect crucial for improving the quality of synthetic speech. Recent theories identify contrast as a central IS element affecting accentuation. This paper presents the results of two experiments aiming to investigate the function of the different levels of contrast within the topic and focus of the utterance, and their effect on the prosody of Greek. Analysis showed that distinguishing between at least two contrast types is important for determining the appropriate accent type, and, therefore, such a distinction should be included in a description of the IS – Prosody interaction. For this description to be useful for practical applications, a framework is required that makes this information accessible to the speech synthesizer. This work reports on such a language-independent framework integration of all identified grammatical and syntactic prerequisites for creating a linguistically enriched input for speech synthesis.


Information Structure Contrast Prosody Prediction Speech Synthesis Annotation Framework 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Arvaniti, A., Baltazani, M.: Intonational Analysis and Prosodic Annotation of Greek Spoken Corpora. In: Jun, S.-A. (ed.) Prosodic Typology: The Phonology of Intonation and Phrasing, pp. 84–117. Oxford University Press, Oxford (2005)Google Scholar
  2. 2.
    Baltazani, M., Jun, S.-A.: Focus and topic intonation in Greek. In: Proceedings of the 14th International Congress of Phonetic Sciences, vol. 2, pp. 1305–1308 (1999)Google Scholar
  3. 3.
    Büring, D.: Semantics, Intonation and Information Structure. In: Ramchad, G., Reiss, C. (eds.) The Oxford Handbook of Linguistic Interfaces. Oxford University Press, Oxford (2007)Google Scholar
  4. 4.
    Dretske, F.J.: Contrastive statements. The Philosophical Review 81, 411–437 (1972)CrossRefGoogle Scholar
  5. 5.
    Gussenhoven, C.: Types of Focus in English. In: Lee, C., Gordon, M., Büring, D. (eds.) Topic and Focus: Cross-linguistic Perspectives on Meaning and Intonation, pp. 83–100. Springer, Heidelberg (2007)Google Scholar
  6. 6.
    Krifka, M.: Basic notions of information structure. In: Fery, C., Krifka, M. (eds.) Interdisciplinary Studies of Information Structure, Potsdam, vol. 6 (2007)Google Scholar
  7. 7.
    Van Leusen, N., Kalman, L.: The Interpretation of Free Focus. In: ILLC Computational Linguistics (1993)Google Scholar
  8. 8.
    Molnár, V.: Contrast from a contrastive perspective. In: Kruiff- Korbayová, I., Steedman, M. (eds.) ESSLLI 2001 Workshop on Information Structure, Discourse Structure and Discourse Semantics (2001)Google Scholar
  9. 9.
    Rooth, M.: A Theory of Focus Interpretation. Natural Language Semantics 1, 75–116 (2001)CrossRefGoogle Scholar
  10. 10.
    Rump, H., Collier, R.: Focus Conditions and the prominence of pitch-accented syllables. Language & Speech 39, 1–17 (1996)Google Scholar
  11. 11.
    Schwarzschild, R.: GIVENness, AvoidF and Other Constraints on the placement of Accent. Natural Language Semantics 7(2), 141–177 (1999)CrossRefGoogle Scholar
  12. 12.
    Selkirk, E.: Contrastive Focus, Givenness and the Unmarked Status of “Discourse-New”. In: Féry, C., Fanselow, G., Krifka, M. (eds.) Working Papers of the SFB632, Interdisciplinary Studies on Information Structure (ISIS), vol. 6, pp. 125–146. Universitätsverlag Potsdam, Potsdam (2007)Google Scholar
  13. 13.
    Steedman, M.: Information structure and the syntax-phonology interface. Linguistic Inquiry 31, 649–689 (2000)CrossRefGoogle Scholar
  14. 14.
    Steedman, M.: Information-Structural Semantics of English Intonation. In: Gordon, M., Büring, D., Lee, C. (eds.) LSA Summer Institute Workshop on Topic and Focus, Santa Barbara, pp. 245–264. Kluwer Academic, Dordrecht (2002)Google Scholar
  15. 15.
    Vallduví, E.: The Informational Component. Garland Publishers, New York (1992)Google Scholar
  16. 16.
    Vallduví, E., Vilkuna, M.: On Rheme and Kontrast. In: Culicover, P., Wagner, M. (eds.) Givenness and Locality. The Limits of Syntax, pp. 79–108. Academic Press, San Diego (1998)Google Scholar
  17. 17.
    Kiss, K.E.: Identificational focus versus information focus. Language 74, 245–273 (1998)CrossRefGoogle Scholar
  18. 18.
    Taylor, P., Black, A., Caley, R.: The architecture of the festival speech synthesis system. In: Proc. 3rd ESCA Workshop on Speech Synthesis, Australia, pp. 147–151 (1998)Google Scholar
  19. 19.
    Pan, S., McKeown, K., Hirschberg, J.: Exploring features from natural language generation for prosody modeling. Computer Speech and Language 16, 457–490 (2002)CrossRefGoogle Scholar
  20. 20.
    Xydas, G., Spiliotopoulos, D., Kouroupetroglou, G.: Modeling Improved Prosody Generation from High-Level Linguistically Annotated Corpora. IEICE Trans. of Inf. and Syst., Special Section on Corpus-Based Speech Technologies 88(3), 510–518 (2005)Google Scholar
  21. 21.
    Black, A., Taylor, P.: Assigning intonation elements and prosodic phrasing for English speech synthesis from high level linguistic input. In: Proc. 3rd Int. Conf. on Spoken Language Processing, Yokohama, Japan, pp. 715–718 (1994)Google Scholar
  22. 22.
    Spiliotopoulos, D., Petasis, G., Kouroupetroglou, G.: A Framework for Language-Independent Analysis and Prosodic Feature Annotation of Text Corpora. In: Sojka, P., Horák, A., Kopeček, I., Pala, K. (eds.) TSD 2008. LNCS (LNAI), vol. 5246, pp. 517–524. Springer, Heidelberg (2008)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2010

Authors and Affiliations

  • Pepi Stavropoulou
    • 1
  • Dimitris Spiliotopoulos
    • 1
  • Georgios Kouroupetroglou
    • 1
  1. 1.Department of Informatics and TelecommunicationsNational and Kapodistrian University of AthensAthensGreece

Personalised recommendations