Volltext-Downloads (blau) und Frontdoor-Views (grau)

The "Kiel Corpus of Read Speech" as a Resource for Prosody Prediction in Speech Synthesis

  • The naturalness of synthetic speech depends strongly on the prediction of appropriate prosody. For the present study the original annotation of the German speech database “Kiel Corpus of Read Speech” was extended automatically with syntactic features, word frequency, and syllable boundaries. Several classification and regression trees for predicting symbolic prosody features, postlexical phonological processes, duration, and F0 were trained on this database. The perceptual evaluation showed that the overall perceptual quality of the German text-to-speech system MARY can be significantly improved by training all models that contribute to prosody prediction on the same database. Furthermore, it showed that the error introduced by symbolic prosody prediction perceptually equals the error produced by a direct method that does not exploit any symbolic prosody features.

Export metadata

Additional Services

Share in Twitter Search Google Scholar


Author:Caren Brinckmann
Parent Title (English):The Second Baltic Conference on HUMAN LANGUAGE TECHNOLOGIES. Proceedings. April 4 - 5, 2005, Tallinn, Estonia
Publisher:Institute of Cybernetics, Institute of the Estonian Language
Place of publication:Tallinn
Editor:Margit Langemets, Priit Penjam
Document Type:Conference Proceeding
Year of first Publication:2005
Date of Publication (online):2017/12/20
Tag:CART; FO prediction; German; database; duration prediction; perceptual evaluation; postlexical processes; symbolic prosody prediction; text-to-speech
GND Keyword:Deutsch; Prosodie; Text-to-Speech; gesprochene Sprache
First Page:101
Last Page:106
DDC classes:400 Sprache / 430 Deutsch
Open Access?:ja
BDSL-Classification:Sprache im 20. Jahrhundert. Gegenwartssprache
Licence (German):License LogoCreative Commons - Namensnennung - Nicht-kommerziell - Weitergabe unter gleichen Bedingungen 4.0 International