Three methods of intonation modeling

  title={Three methods of intonation modeling},
  author={Ann K. Syrdal and Gregor M{\"o}hler and Kurt E. Dusterhoff and Alistair Conkie and Alan W. Black},
This paper compares di erent methods of generating intonation for an American English Text-to-Speech synthesis system. We look at a primarily rule-based approach and two data-driven approaches. For data-driven modeling we used two separate data sets, each representing a somewhat di erent prosodic style. One database was recordings of a portion of 1989 Wall Street Journal text from the Penn Treebank Project. The second database was recordings of interactive prompts used in telephone network… CONTINUE READING
Highly Cited
This paper has 22 citations. REVIEW CITATIONS

From This Paper

Figures, tables, and topics from this paper.
16 Citations
9 References
Similar Papers


Publications referenced by this paper.
Showing 1-9 of 9 references

Diphones concate nation using a harmonic plus noise model of speech

  • J. Schroeter Y. Stylianou, T. Dutoit
  • 1997
Highly Influential
7 Excerpts

The festival speech synthesis system

  • A. Black, P. Taylor, R. Caley
  • 1998
2 Excerpts

ohler. Theoriebasierte Modellierung der deutschen Intonation fur die Sprachsynthese (Theory based modeling of German intonation for speech synthe sis)

  • M Gregor
  • University of Stuttgart, Institute of Natural Lan…
  • 1998
1 Excerpt

Regelbasierte Generierung nat urlich klin gender Intonationsmuster des Amerikanischen Englisch (Rule-based generation of naturally sounding intonation patterns of American English)

  • Matthias Jilka
  • University of Stuttgart, Institute of Natural…
  • 1996
3 Excerpts

Similar Papers

Loading similar papers…