Please use this identifier to cite or link to this item:
|Title:||Evaluation of a neural network segmental duration model for Portuguese|
|Authors:||Teixeira, João Paulo|
|Citation:||Teixeira, João Paulo; Freitas. D. (2002) - Evaluation of a neural network segmental duration model for Portuguese. In IEEE Workshop on Speech Synthesis. Santa Mónica – USA.|
|Abstract:||This paper presents a segmental duration model, that, as far as the authors know, is the first published for European Portuguese, with objective and subjective evaluations. The model is aimed at TTS applications and is based on an ANN, trained with a resilient back-propagation algorithm. Using a substantial amount of training data and a carefully selected set of input factors, the standard deviation of the error of segmental duration estimations reaches 19 ms and the correlation coefficient goes above 0.9. Several models have been published for other languages with objective and subjective good performances. The methodology of construction of the model, the importance of the used factors and the neural network will be presented, together with the evaluation of the model, allowing a comparison with other models for other languages.|
|Appears in Collections:||DE - Artigos em Proceedings Não Indexados ao ISI/Scopus|
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.