Classification-Based Detection of Glottal Closure Instants from Speech Signals

Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F49777513%3A23520%2F17%3A43932654" target="_blank" >RIV/49777513:23520/17:43932654 - isvavai.cz</a>
Result on the web
<a href="https://pdfs.semanticscholar.org/7733/cc382ff4110debd11a188674f317a0e5dc89.pdf" target="_blank" >https://pdfs.semanticscholar.org/7733/cc382ff4110debd11a188674f317a0e5dc89.pdf</a>
DOI - Digital Object Identifier
<a href="http://dx.doi.org/10.21437/Interspeech.2017-213" target="_blank" >10.21437/Interspeech.2017-213</a>

Result language
angličtina
Original language name
Classification-Based Detection of Glottal Closure Instants from Speech Signals
Original language description
In this paper a classification-based method for the automatic detection of glottal closure instants (GCIs) from the speech sig- nal 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 F 1 score is 97.27%. In addition, despite using the speech signal only, the proposed method behaves com- parably to a method utilizing the glottal signal. The method is also compared with three existing GCI detection algorithms on publicly available databases.
Czech name
—
Czech description
—

Project
<a href="/en/project/GA16-04420S" target="_blank" >GA16-04420S: Combining phonetic and corpus-based approaches to remedy disruptive effects in synthetic speech</a><br>
Continuities
P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)

Publication year
2017
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Article name in the collection
Proceedings of the 18th Annual Conference of the International Speech Communication Association (Interspeech 2017)
ISBN
978-1-5108-4876-4
ISSN
—
e-ISSN
—
Number of pages
5
Pages from-to
3053-3057
Publisher name
Curran Associates, Inc.
Place of publication
Red Hook, NY
Event location
Stockholm, Sweden
Event date
Aug 20, 2017
Type of event by nationality
WRD - Celosvětová akce
UT code for WoS article
000457505000631

Similar results(10)