Konferenzbeitrag

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.

Language
Englisch

Subject
Deutsch
gesprochene Sprache
Text-to-Speech
Prosodie
Germanische Sprachen; Deutsch

Event
Geistige Schöpfung
(who)
Brinckmann, Caren
Event
Veröffentlichung
(who)
Tallinn : Institute of Cybernetics, Institute of the Estonian Language
(when)
2017-12-20

URN
urn:nbn:de:bsz:mh39-68652
Last update
06.03.2025, 9:00 AM CET

Data provider

This object is provided by:
Leibniz-Institut für Deutsche Sprache - Bibliothek. If you have any questions about the object, please contact the data provider.

Object type

  • Konferenzbeitrag

Associated

  • Brinckmann, Caren
  • Tallinn : Institute of Cybernetics, Institute of the Estonian Language

Time of origin

  • 2017-12-20

Other Objects (12)