Sixth European Conference on Speech Communication and Technology
Many aspects of prosody prediction in speech synthesis could be improved, from placement of symbolic accent and phrase boundary markers to control of continuously varying parameters (e.g., duration, fundamental frequency). The goal of this work is to develop algorithms for predicting aspects of fundamental frequency typically said to have gradient variation: pitch range and prominence. In addition, the results of the automatic training methodology are used to investigate differences in prominence patterns associated with different genres of speech.
Full Paper (PDF) Gnu-Zipped Postscript
Bibliographic reference. Bulyko, Ivan / Ostendorf, Mari (1999): "Predicting gradient F0 variation: pitch range and accent prominence", In EUROSPEECH'99, 1819-1822.