Publications

BibTex format

@article{Zhang:2020:10.1109/JBHI.2019.2907286,
author = {Zhang, Z and Han, J and Qian, K and Janott, C and Guo, Y and Schuller, B},
doi = {10.1109/JBHI.2019.2907286},
journal = {IEEE Journal of Biomedical and Health Informatics},
pages = {300--310},
title = {Snore-GANs: improving automatic snore sound classification with synthesized data},
url = {http://dx.doi.org/10.1109/JBHI.2019.2907286},
volume = {24},
year = {2020}
}

Download

RIS format (EndNote, RefMan)

TY  - JOUR
AB  - One of the frontier issues that severely hamper the development of automatic snore sound classification (ASSC) associates to the lack of sufficient supervised training data. To cope with this problem, we propose a novel data augmentation approach based on semi-supervised conditional Generative Adversarial Networks (scGANs), which aims to automatically learn a mapping strategy from a random noise space to original data distribution. The proposed approach has the capability of well synthesizing ‘realistic’ high-dimensional data, while requiring no additional annotation process. To handle the mode collapse problem of GANs, we further introduce an ensemble strategy to enhance the diversity of the generated data. The systematic experiments conducted on a widely used Munich-Passau snore sound corpus demonstrate that the scGANs-based systems can remarkably outperform other classic data augmentation systems, and are also competitive to other recently reported systems for ASSC.
AU  - Zhang,Z
AU  - Han,J
AU  - Qian,K
AU  - Janott,C
AU  - Guo,Y
AU  - Schuller,B
DO  - 10.1109/JBHI.2019.2907286
EP  - 310
PY  - 2020///
SN  - 2168-2194
SP  - 300
TI  - Snore-GANs: improving automatic snore sound classification with synthesized data
T2  - IEEE Journal of Biomedical and Health Informatics
UR  - http://dx.doi.org/10.1109/JBHI.2019.2907286
UR  - http://hdl.handle.net/10044/1/67812
VL  - 24
ER  -

Download

ProfessorBjoernSchuller

Contact

Location

Summary

Citation

BibTex format

RIS format (EndNote, RefMan)