Title: Using extreme gradient boosting to detect glottal closure instants in speech signal
Authors: Matoušek, Jindřich
Tihelka, Daniel
Citation: MATOUŠEK, J., TIHELKA, D. Using extreme gradient boosting to detect glottal closure instatnts in speech singal. In: 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2019). New York: IEEE, 2019. s. 6515-6519. ISBN 978-1-4799-8131-1 , ISSN 1520-6149.
Issue Date: 2019
Publisher: IEEE
Document type: konferenční příspěvek
URI: 2-s2.0-85069464575
ISBN: 978-1-4799-8131-1
ISSN: 1520-6149
Keywords in different language: glottal closure instant (GCI);pitch mark;detection;classification;extreme gradient boosting
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.
Rights: Plný text je přístupný v rámci univerzity přihlášeným uživatelům.
Appears in Collections:Konferenční příspěvky / Conference Papers (KKY)

Files in This Item:
File SizeFormat 
ICASSP_2019_Matousek_UsingExtremeGradientBoosting.pdf220,98 kBAdobe PDFView/Open    Request a copy

Please use this identifier to cite or link to this item: http://hdl.handle.net/11025/36660

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.

  1. DSpace at University of West Bohemia
  2. Publikační činnost / Publications
  3. OBD