Skip to content

Publications

Detail of publication

Citation

Matoušek, J. : Automatic Pitch-Synchronous Phonetic Segmentation with Context-Independent HMMs . Text, Speech and Dialogue, proceedings of the 12th International Conference TSD 2009, Lecture Notes in Artificial Intelligence, p. 178-185, Springer, Berlin-Heidelberg, Germany, 2009.

Additional information


Springerlink

Abstract

This paper deals with an HMM-based automatic phonetic segmentation (APS) system. In particular, the use of a pitch-synchronous (PS) coding scheme within the context-independent (CI) HMM-based APS system is examined and compared to the "more traditional'' pitch-asynchronous (PA) coding schemes for a given Czech male voice. For bootstrap-initialised CI-HMMs, exploited when some (manually) pre-segmented data are available, the proposed PS coding scheme performed best, especially in combination with CART-based refinement of the automatically segmented boundaries. For flat-start-initialised CI-HMMs, an inferior initialisation method used when no pre-segmented data are at disposal, standard PA coding schemes with longer parameterization shifts yielded better results. The results are also compared to the results obtained for APS systems with context-dependent (CD) HMMs. It was shown that, at least for the researched male voice, multiple-mixture CI-HMMs outperform CD-HMMs in the APS task.

Detail of publication

Title: Automatic Pitch-Synchronous Phonetic Segmentation with Context-Independent HMMs
Author: Matoušek, J.
Language: English
Date of publication: 13 Sep 2009
Year: 2009
Type of publication: Papers in proceedings of reviewed conferences
Book title: Text, Speech and Dialogue, proceedings of the 12th International Conference TSD 2009
Series: Lecture Notes in Artificial Intelligence
Page: 178 - 185
ISBN: 978-3-642-04207-2
ISSN: 0302-9743
Publisher: Springer
Address: Berlin-Heidelberg, Germany
Date: 13 Sep 2009 - 18 Sep 2009
/ 2009-10-07 12:19:23 /

Keywords

automatic phonetic segmentation, pitch-synchronous coding, context-independent hidden Markov models, speech synthesis, unit selection

BibTeX

@INPROCEEDINGS{MatousekJ_2009_Automatic,
 author = {Matou\v{s}ek, J.},
 title = {Automatic Pitch-Synchronous Phonetic Segmentation with Context-Independent HMMs},
 year = {2009},
 publisher = {Springer},
 address = {Berlin-Heidelberg, Germany},
 pages = {178-185},
 booktitle = {Text, Speech and Dialogue, proceedings of the 12th International Conference TSD 2009},
 series = {Lecture Notes in Artificial Intelligence},
 ISBN = {978-3-642-04207-2},
 ISSN = {0302-9743},
 url = {http://www.kky.zcu.cz/en/publications/MatousekJ_2009_Automatic},
}