Přejít na obsah

Detail publikace

Citace

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.

PDF ke stažení

PDF

Abstrakt

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 publikace

Název: Identification and Automatic Detection of Parasitic Speech Sounds
Autor: Matoušek, J. ; Skarnitzl, R ; Machač, P ; Trmal, J.
Název - česky: Identifikace a automatická detekce parazitních řečových zvuků
Jazyk publikace: anglicky
Datum vydání: 6.9.2009
Rok vydání: 2009
Typ publikace: Stať ve sborníku
Název knihy: INTERSPEECH 2009, proceedings of 10th Annual Conference of International Speech Communication Association
Strana: 876 - 879
ISSN: 1990-9772
Nakladatel: ISCA
Místo vydání: Brighton, Great Britain
Datum: 6.9.2009 - 10.9.2009
/ 2009-10-07 12:17:48 /

Klíčová slova

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},
}