DSpace DSpace UPC
 Català   Castellano   English  

E-prints UPC >
Altres >
Enviament des de DRAC >

Empreu aquest identificador per citar o enllaçar aquest ítem: http://hdl.handle.net/2117/9608

Arxiu Descripció MidaFormat
TTSevaluation.pdf461,59 kBAdobe PDFThumbnail

Citació: Sainz, I. [et al.]. TTS evaluation campaign with a common spanish database. A: International Conference on Language Resources and Evaluation. "Seventh Int. Conf. on Language Resources and Evaluation (LREC)". Valleta: 2010, p. 2155-2160.
Títol: TTS evaluation campaign with a common spanish database
Autor: Sainz, Iñaki; Navas, Eva; Hernáez, Inma; Bonafonte Cávez, Antonio Veure Producció científica UPC; Campillo, Francisco
Data: 2010
Tipus de document: Conference report
Resum: This paper describes the first TTS evaluation campaign designed for Spanish. Seven research institutions took part in the evaluation campaign and developed a voice from a common speech database provided by the organisation. Each participating team had a period of seven weeks to generate a voice. Next, a set of sentences were released and each team had to synthesise them within a week period. Finally, some of the synthesised test audio files were subjectively evaluated via an online test according to the following criteria: similarity to the original voice, naturalness and intelligibility. Box-plots, Wilcoxon tests and WER have been generated in order to analyse the results. Two main conclusions can be drawn: On the one hand, there is considerable margin for improvement to reach the quality level of the natural voice. On the other hand, two systems get significantly better results than the rest: one is based on statistical parametric synthesis and the other one is a concatenative system that makes use of a sinusoidal model to modify both prosody and smooth spectral joints. Therefore, it seems that some kind of spectral control is needed when building voices with a medium size database for unrestricted domains.
ISBN: 2-9517408-6-7
URI: http://hdl.handle.net/2117/9608
Versió de l'editor: http://www.lrec-conf.org/proceedings/lrec2010/pdf/456_Paper.pdf
Apareix a les col·leccions:VEU - Grup de Tractament de la Parla. Ponències/Comunicacions de congressos
Departament de Teoria del Senyal i Comunicacions. Ponències/Comunicacions de congressos
Altres. Enviament des de DRAC

Stats Mostra les estadístiques d'aquest ítem

SFX Query

Aquest ítem (excepte textos i imatges no creats per l'autor) està subjecte a una llicència de Creative Commons Llicència Creative Commons
Creative Commons


Valid XHTML 1.0! Programari DSpace Copyright © 2002-2004 MIT and Hewlett-Packard Comentaris
Universitat Politècnica de Catalunya. Servei de Biblioteques, Publicacions i Arxius