Skip to content

Detail of publication

Citation

Matoušek, J. and Skarnitzl, R and Machač, P and Trmal, J. : Identification and Automatic Detection of Parasitic Speech Sounds . INTERSPEECH 2009, proceedings of 10th Annual Conference of International Speech Communication Association, p. 876-879, ISCA, Brighton, Great Britain, 2009.

Download PDF

PDF

Abstract

This paper presents initial experiments with the identification and automatic detection of parasitic sounds in speech signals. The main goal of this study is to identify such sounds in the source recordings for unit-selection-based speech synthesis systems and thus to avoid their unintended usage in synthesised speech. The first part of the paper describes the phonetic analysis and identification of parasitic phenomena in recordings of two Czech speakers. In the second part, experiments with the automatic detection of parasitic sounds using HMM-based and BVM classifiers are presented. The results are encouraging, especially those for glottalization phenomena.

Detail of publication

Title: Identification and Automatic Detection of Parasitic Speech Sounds
Author: Matoušek, J. ; Skarnitzl, R ; Machač, P ; Trmal, J.
Language: English
Date of publication: 6 Sep 2009
Year: 2009
Type of publication: Papers in proceedings of reviewed conferences
Book title: INTERSPEECH 2009, proceedings of 10th Annual Conference of International Speech Communication Association
Page: 876 - 879
ISSN: 1990-9772
Publisher: ISCA
Address: Brighton, Great Britain
Date: 6 Sep 2009 - 10 Sep 2009
/ 2009-10-07 12:17:48 /

Keywords

parasitic speech sound, linguistic naturalness, speech synthesis, unit selection, HMM, BVM

BibTeX

@INPROCEEDINGS{MatousekJ_2009_Identificationand,
 author = {Matou\v{s}ek, J. and Skarnitzl, R and Macha\v{c}, P and Trmal, J.},
 title = {Identification and Automatic Detection of Parasitic Speech Sounds},
 year = {2009},
 publisher = {ISCA},
 address = {Brighton, Great Britain},
 pages = {876-879},
 booktitle = {INTERSPEECH 2009, proceedings of 10th Annual Conference of International Speech Communication Association},
 ISSN = {1990-9772},
 url = {http://www.kky.zcu.cz/en/publications/MatousekJ_2009_Identificationand},
}