Influence of Language Parameters Selection on the Coarticulation of the Phonemes for Prosody Training in TTS by Neural Networks

0404799 - UIVT-O 20030020 RIV AT eng C - Konferenční příspěvek (zahraniční konf.)
Tučková, J. - Šebesta, Václav
Influence of Language Parameters Selection on the Coarticulation of the Phonemes for Prosody Training in TTS by Neural Networks.
Artificial Neural Nets and Genetic Algorithms. Wien: SpringerVerlag, 2003 - (Pearson, D.; Steele, N.; Albrecht, R.), s. 85-90. ISBN 3-211-00743-1.
[ICANNGA'2003 /6./. Roanne (FR), 23.04.2003-25.04.2003]
Grant CEP: GA ČR GA102/02/0124
Výzkumný záměr: AV0Z1030915
Klíčová slova: text-to-speech synthesis * parameters selection * prosody control

This contribution describes the influence of the Czech language parameters selection on the coarticulation of the phonemes for the modelling of prosody features by the artificial neural network (ANN) in a text-to-speech (TTS) synthesis. The GUHA method and neural network pruning can be used for this reason. In our work we analyzed the errors between the target and the calculated values of F0 and D from the point of view of the different context of speech units.
Trvalý link: http://hdl.handle.net/11104/0125032