0403694 - UIVT-O 200982 RIV DE eng M - Monography Chapter
Tučková, Jana - Šebesta, Václav
Optimization of Input Data for Fundamental Frequency Modelling by Neural Networks.
Papers in Phonetics and Speech Processing. Frankfurt am Main: Hector, 2000 - (Palková, Z.; Wodarz, H.), s. 161-175. Forum Phoneticum, 70. ISBN 3-930110-18-0
R&D Projects: GA ČR GA102/96/K087; GA AV ČR IAA2030801
Institutional research plan: AV0Z1030915
Subject RIV: BA - General Mathematics

A speech signal synthesis in real time, with a nonlimited vocabulary is very complicated for all languages. These synthesizers usually work in the frequency domain and the fundamental frequency contours F0 must be determined for all phonemes or diphones by conventional equipment based on linguistic rules (Tučková, Vích 1997). Our effort is to minimize the difference between the synthetic speech of the synthesizer, which is usually more monotonous, and the natural speech of people...
Permanent Link: http://hdl.handle.net/11104/0123991