Number of the records: 1
Applications and Science in Soft Computing
- 1.
SYSNO ASEP 0405193 Document Type M - Monograph Chapter R&D Document Type Monograph Chapter Title Optimisation of Neural Network Topology and Input Parameters for Prosody Modelling of Synthetic Speech Author(s) Šebesta, Václav (UIVT-O) SAI, RID
Tučková, J. (CZ)Source Title Applications and Science in Soft Computing / Lotfi A. ; Garibaldi J.. - Berlin : Springer, 2004 - ISSN 1615-3871 - ISSN 1867-5662 - ISBN 978-3-540-40856-7 Pages s. 9-16 Number of pages 8 s. Action RASC 2002. International Conference on Recent Advances in Soft Computing /4./ Event date 12.12.2002-13.12.2002 VEvent location Nottingham Country GB - United Kingdom Event type WRD Language eng - English Country DE - Germany Keywords feature selection ; text-to-speech processing ; prosody modelling ; speech synthesis ; neural network utilization Subject RIV BB - Applied Statistics, Operational Research R&D Projects GA102/02/0124 GA ČR - Czech Science Foundation (CSF) CEZ 1030915 UT WOS 000189228800002 DOI 10.1007/978-3-540-45240-9_2 Annotation We try to investigate methods for extracting knowledge from existing continuous speech databases for optimisation of neural network topology to improve the generalization ability of ANN. The ANN for the modelling of fundamental frequency and duration of a speech unit for a Text-to-Speech synthesis are trained by natural speech. The principle of synthesizer is based on the concatenation of speech units. We also use speech unit segmentation of a text for prosody modelling. Workplace Institute of Computer Science Contact Tereza Šírová, sirova@cs.cas.cz, Tel.: 266 053 800 Year of Publishing 2004
Number of the records: 1