Prosody modelling for a text-to-speech system by artificial neural networks.

Result code in IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F67985807%3A_____%2F00%3A13000143" target="_blank" >RIV/67985807:_____/00:13000143 - isvavai.cz</a>

Alternative codes found

RIV/67985882:_____/00:13000143

Result on the web

—

DOI - Digital Object Identifier

—

Result language

angličtina

Original language name

Prosody modelling for a text-to-speech system by artificial neural networks.

Original language description

In the paper it is searched for a solution of two problems: speech naturalness requirements and optimal choice of phonetic and phonologic parameters for prosody modelling. The neural network has been used for fundamental frequency determination and for the duration of phonemes in prosody modelling. For the minimisation of the number of input parameters and for the reduction of the neural net structure redundancy, the GUHA method and pruning of neural networks can be suitable tools.

Czech name

—

Czech description

—

Type

D - Article in proceedings

CEP classification

BD - Information theory

OECD FORD branch

—

Project

Result was created during the realization of more than one project. More information in the Projects tab.

Continuities

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)

Publication year

2000

Confidentiality

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Article name in the collection

Proceedings of the IASTED International Conference Signal and Image Processing - SIP 2000.

ISBN

0-88986-308-3

ISSN

—

e-ISSN

—

Number of pages

6

Pages from-to

—

Publisher name

IASTED/Acta Press

Place of publication

Anaheim

Event location

—

Event date

—

Type of event by nationality

—

UT code for WoS article

—