Evaluation of a Segmental Durations Model for TTS

• Type: Article in International Conference Proceedings Book
• Date: 2003

Authors

João Teixeira (Author) Other; Diamantino Freitas (Author) FEUP

Conference proceedings National

Title: PROPOR’2003 - VI Encontro para o Processamento Computacional da Língua Portuguesa Escrita e Falada

Pages: 40-48

Universidade do Algarve-FCHS, Faro, Portugal, 26 e 27 de Junho de 2003

Other information

DOI: 10.1007/3-540-45011-4_6

Resumo (PT): Apresentado e publicado nas actas do PROPOR’2003 - VI Encontro para o Processamento Computacional da Língua Portuguesa Escrita e Falada, 6th Workshop on Computational Processing of the Portuguese Language - Written and Spoken, que se realizou na Universidade do Algarve-FCHS, Faro, Portugal, em 26 e 27 de Junho de 2003 ISBN 3-540-40436-8

Abstract (EN): In this paper we present a condensed description of a European Portuguese segmental duration's model for TTS purposes and concentrate on its evaluation. This model is based on artificial neural networks. The evaluation of the model quality was made by comparison with read speech. The standard deviation reached in test set is 19.5 ms and the linear correlation coefficient is 0.84. The model is perceptually evaluated with 4.12 against 4.30 for natural human read speech in a scale of 5. © Springer-Verlag Berlin Heidelberg 2003.

Language: English

Type (Professor's evaluation): Scientific

No. of pages: 9