Přejít na obsah

Publikace

Detail publikace

Citace

Matoušek, J. and Tihelka, D. : Classification-Based Detection of Glottal Closure Instants from Speech Signals . Interspeech 2017, p. 3053-3057, Stockholm, Sweden, 2017.

PDF ke stažení

PDF

Abstrakt

In this paper a classification-based method for the automatic detection of glottal closure instants (GCIs) from the speech signal is proposed. Peaks in the speech waveforms are taken as candidates for GCI placements. A classification framework is used to train a classification model and to classify whether or not a peak corresponds to the GCI. We show that the detection accuracy in terms of F1 score is 97.27%. In addition, despite using the speech signal only, the proposed method behaves comparably to a method utilizing the glottal signal. The method is also compared with three existing GCI detection algorithms on publicly available databases.

Detail publikace

Název: Classification-Based Detection of Glottal Closure Instants from Speech Signals
Autor: Matoušek, J. ; Tihelka, D.
Jazyk publikace: anglicky
Rok vydání: 2017
Typ publikace: Stať ve sborníku
Název knihy: Interspeech 2017
Strana: 3053 - 3057
DOI: 10.21437/Interspeech.2017-213
Místo vydání: Stockholm, Sweden
/ 2019-09-05 16:07:19 /

BibTeX

@INPROCEEDINGS{MatousekJ_2017_Classification-Based,
 author = {Matou\v{s}ek, J. and Tihelka, D.},
 title = {Classification-Based Detection of Glottal Closure Instants from Speech Signals},
 year = {2017},
 address = {Stockholm, Sweden},
 pages = {3053-3057},
 booktitle = {Interspeech 2017},
 doi = {10.21437/Interspeech.2017-213},
 url = {http://www.kky.zcu.cz/en/publications/MatousekJ_2017_Classification-Based},
}