TY  - CHAP
U1  - Konferenzveröffentlichung
A1  - Brinckmann, Caren
ED  - Langemets, Margit
ED  - Penjam, Priit
T1  - The "Kiel Corpus of Read Speech" as a Resource for Prosody Prediction in Speech Synthesis
T2  - The Second Baltic Conference on HUMAN LANGUAGE TECHNOLOGIES. Proceedings. April 4 - 5, 2005, Tallinn, Estonia
N2  - 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.
KW  - Deutsch
KW  - gesprochene Sprache
KW  - Text-to-Speech
KW  - Prosodie
KW  - text-to-speech
KW  - database
KW  - CART
KW  - symbolic prosody prediction
KW  - postlexical processes
KW  - duration prediction
KW  - FO prediction
KW  - perceptual evaluation
KW  - German
Y1  - 2005
U6  - https://nbn-resolving.org/urn:nbn:de:bsz:mh39-68652
UN  - https://nbn-resolving.org/urn:nbn:de:bsz:mh39-68652
SN  - 9985-894-83-9
SB  - 9985-894-83-9
SP  - 101
EP  - 106
PB  - Institute of Cybernetics, Institute of the Estonian Language
CY  - Tallinn
ER  -