Skip to content

Publications

Detail of publication

Citation

Legát, M and Matoušek, J. : Identifying Concatenation Discontinuities by Hierarchical Divisive Clustering of Pitch Contours . Text, Speech and Dialogue, Proceedings of the 14th International Conference TSD 2011, Lecture Notes in Artificial Intelligence, vol. 6836, p. 171-178, Springer, 2011.

Additional information


Springerlink

Abstract

In this paper, we present the results of a clustering experiment, the aim of which was to show whether or not the proximity of pitch contours is sufficient condition for perceptually smooth transitions at concatenation points in concatenative speech synthesis. The experiment was motivated by a previous finding which had shown that the support vector machine (SVM) classifiers are capable of separating with a high accuracy perceptually continuous and discontinuous joins using the pitch contours extracted from the vicinity of concatenation points as predictors. The experiment has shown that clustering of observations in a form of pitch contours represented in different scales using the euclidean distance as a metric does not prove to be a reliable way of identifying discontinuities at concatenation points.

Detail of publication

Title: Identifying Concatenation Discontinuities by Hierarchical Divisive Clustering of Pitch Contours
Author: Legát, M ; Matoušek, J.
Language: English
Date of publication: 1 Sep 2011
Year: 2011
Type of publication: Papers in journals
Book title: Text, Speech and Dialogue, Proceedings of the 14th International Conference TSD 2011
Series: Lecture Notes in Artificial Intelligence
Číslo vydání: 6836
Page: 171 - 178
ISSN: 0302-9743
Publisher: Springer
Date: 1 Sep 2011 - 5 Sep 2011
/ 2014-01-26 22:03:02 /

Keywords

speech synthesis, unit selection, concatenation cost, pitch contours, hierarchical divisive clustering

BibTeX

@INCOLLECTION{LegatM_2011_Identifying,
 author = {Leg\'{a}t, M and Matou\v{s}ek, J.},
 title = {Identifying Concatenation Discontinuities by Hierarchical Divisive Clustering of Pitch Contours},
 year = {2011},
 publisher = {Springer},
 volume = {6836},
 pages = {171-178},
 booktitle = {Text, Speech and Dialogue, Proceedings of the 14th International Conference TSD 2011},
 series = {Lecture Notes in Artificial Intelligence},
 ISSN = {0302-9743},
 url = {http://www.kky.zcu.cz/en/publications/LegatM_2011_Identifying},
}