5th European Conference on Speech Communication and Technology

Rhodes, Greece
September 22-25, 1997

Speech Timing in Slovenian TTS

Jerneja Gros, Nikola Pavesic, France Mihelic

Artificial Perception Laboratory, Faculty of Electrical Engineering, University of Ljubljana, Slovenia

Speech timing at different speaking rates was studied for the Slovenian language and the results were applied for duration modelling in the Slovenian text-to-speech system S5 [1]. In order to enable the synthesiser to pronounce input text with several speaking rates, tests were made to study the impact of speaking rate on syllable duration and duration of individual phonemes and phoneme groups for the Slovenian language [2]. A two-level approach to durational modelling is described. A method for segment duration prediction was developed, which adapts a word with an intrinsic duration to the desired extrinsic duration, taking into account how stretching and squeezing apply to duration of individual segments.


  1. J. Gros, N. Pavesic, F. Mihelic, "A text-to-speech system for the Slovenian language", Proc. EUSIPCO'96, Trieste, pp. 1043-1046, 1996.
  2. J. Gros, N. Pavesic, F. Mihelic, "Syllable and segment duration at different speaking rates in the Slovenian language", Proc. EUROSPEECH'97, Rhodes, 1997.

Full Paper
Acoustic Examples:   #1   #2   #3   #4  

Bibliographic reference.  Gros, Jerneja / Pavesic, Nikola / Mihelic, France (1997): "Speech timing in Slovenian TTS", In EUROSPEECH-1997, 323-326.