Title: | A Comparison of Convolutional Neural Networks for Glottal Closure Instant Detection from Raw Speech |
Authors: | Matoušek, Jindřich Tihelka, Daniel |
Citation: | MATOUŠEK, J. TIHELKA, D. A Comparison of Convolutional Neural Networks for Glottal Closure Instant Detection from Raw Speech. In 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2021). New York: IEEE, 2021. s. 6938-6942. ISBN: 978-1-72817-605-5 , ISSN: 1520-6149 |
Issue Date: | 2021 |
Publisher: | IEEE |
Document type: | konferenční příspěvek ConferenceObject |
URI: | 2-s2.0-85115048595 http://hdl.handle.net/11025/47270 |
ISBN: | 978-1-72817-605-5 |
ISSN: | 1520-6149 |
Keywords in different language: | glottal closure instant (GCI);detection;deep learning;convolutional neural network |
Abstract in different language: | In this paper, we continue to investigate the use of machine learning for the automatic detection of glottal closure instants (GCIs) from raw speech. We compare several deep one-dimensional convolutional neural network architectures on the same data and show that the InceptionV3 model yields the best results on the test set. On publicly available databases, the proposed 1D InceptionV3 outperforms XGBoost, a non-deep machine learning model, as well as other traditional GCI detection algorithms. |
Rights: | Plný text je přístupný v rámci univerzity přihlášeným uživatelům. © IEEE |
Appears in Collections: | Konferenční příspěvky / Conference Papers (KKY) OBD |
Files in This Item:
File | Size | Format | |
---|---|---|---|
Matousek_A_Comparison_of_Convolutional_Neural_Networks_ICASSP2021.pdf | 1,81 MB | Adobe PDF | View/Open Request a copy |
Please use this identifier to cite or link to this item:
http://hdl.handle.net/11025/47270
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.