Skip to content

Detail of publication

Citation

Matoušek, J. and Tihelka, D. : Using Extreme Gradient Boosting to Detect Glottal Closure Instants in Speech Signal . IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), p. 6515-6519, Brighton, Great Britain, 2019.

Download PDF

PDF

Abstract

In this paper, we continue to investigate the use of classifiers for the automatic detection of glottal closure instants (GCIs) from the speech signal. We focus on extreme gradient boosting (XGB), a fast and powerful implementation of a gradient boosting algorithm. We show that XGB outperforms other classifiers, achieving GCI detection accuracy F 1 = 98.55% and AUC = 99.90%. The proposed XGB model is also shown to outperform other existing GCI detection algorithms on publicly available databases. Despite using much less training data, the performance of XGB is comparable to a deep convolutional neural network based approach, especially when it is tested on voices that were not included in the training data.

Detail of publication

Title: Using Extreme Gradient Boosting to Detect Glottal Closure Instants in Speech Signal
Author: Matoušek, J. ; Tihelka, D.
Language: English
Year: 2019
Type of publication: Papers in proceedings of reviewed conferences
Book title: IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
Page: 6515 - 6519
DOI: 10.1109/ICASSP.2019.8683889
Address: Brighton, Great Britain
/ 2019-08-22 10:04:23 /

BibTeX

@INPROCEEDINGS{MatousekJ_2019_UsingExtreme,
 author = {Matou\v{s}ek, J. and Tihelka, D.},
 title = {Using Extreme Gradient Boosting to Detect Glottal Closure Instants in Speech Signal},
 year = {2019},
 address = {Brighton, Great Britain},
 pages = {6515-6519},
 booktitle = {IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)},
 doi = {10.1109/ICASSP.2019.8683889},
 url = {http://www.kky.zcu.cz/en/publications/MatousekJ_2019_UsingExtreme},
}