Skip to content

Detail of publication

Citation

Vít, J and Matoušek, J. : Concatenation Artifact Detection Trained from Listeners Evaluations . Text, Speech and Dialogue, Proceedings of the 16th International Conference TSD 2013, Lecture Notes in Artificial Intelligence, vol. 8082, p. 169-176, Springer, 2013.

Additional information


Springerlink

Abstract

Unit selection is known for its ability to produce high-quality synthetic speech. In contrast with HMM-based synthesis, it produces more natural speech but it may suffer from sudden quality drops at concatenation points. The danger of quality deterioration can be reduced (but, unfortunately, not eliminated) by using very large speech corpora. In this paper, our first experiment with automatic artifact detection is presented. Firstly, a brief description of artifacts is given. Then, a listening test experiment, in which listeners evaluated speech synthesis artifacts, is described. The data gathered during the listening test were then used to train an SVM classifer. Finally, results of the SVM-based artifact detection in synthetic speech are discussed.

Detail of publication

Title: Concatenation Artifact Detection Trained from Listeners Evaluations
Author: Vít, J ; Matoušek, J.
Language: English
Date of publication: 5 Sep 2013
Year: 2013
Type of publication: Papers in proceedings of reviewed conferences
Book title: Text, Speech and Dialogue, Proceedings of the 16th International Conference TSD 2013
Series: Lecture Notes in Artificial Intelligence
Číslo vydání: 8082
Page: 169 - 176
DOI: 10.1007/978-3-642-40585-3_22
ISBN: 978-3-642-40584-6
ISSN: 0302-9743
Publisher: Springer
Date: 1 Sep 2013 - 5 Sep 2013
/ 2016-01-13 16:26:25 /

Keywords

speech synthesis, unit selection, error detection

BibTeX

@INCOLLECTION{VitJ_2013_Concatenation,
 author = {V\'{i}t, J and Matou\v{s}ek, J.},
 title = {Concatenation Artifact Detection Trained from Listeners Evaluations},
 year = {2013},
 publisher = {Springer},
 volume = {8082},
 pages = {169-176},
 booktitle = {Text, Speech and Dialogue, Proceedings of the 16th International Conference TSD 2013},
 series = {Lecture Notes in Artificial Intelligence},
 ISBN = {978-3-642-40584-6},
 ISSN = {0302-9743},
 doi = {10.1007/978-3-642-40585-3_22},
 url = {http://www.kky.zcu.cz/en/publications/VitJ_2013_Concatenation},
}