TY - JOUR
T1 - Breaking through data scarcity
T2 - A novel diffusion model approach for snoring sound augmentation and classification
AU - Jia, Tianrui
AU - Zhang, Haojie
AU - Wu, Hanhan
AU - Sun, Qiyang
AU - Jing, Xin
AU - Meng, Boyang
AU - Shen, Lin
AU - Wang, Liang
AU - Qian, Kun
AU - Zhang, Ye
AU - Hu, Bin
AU - Schultz, Tanja
AU - Schuller, Björn W.
AU - Yamamoto, Yoshiharu
N1 - Publisher Copyright:
© 2026
PY - 2026/5/1
Y1 - 2026/5/1
N2 - Snoring can stem from various upper regions of the upper airways – the excitation location is closely linked to the unique acoustic characteristics of snore sounds, playing a vital role in sleep monitoring. The Munich-Passau Snore Sound Corpus (MPSSC) is the largest database for snoring-based auxiliary diagnosis, offering valuable data for sleep disorder research and diagnosis. However, in MPSSC, there are issues such as the small total number of samples and the uneven sample distribution. Some rare diseases have only a few case samples, failing to meet the need for sufficient learning data. To address these issues, we propose an end-to-end method for high-quality snoring audio generation for data augmentation. This method includes a Rectified-Flow-based 1D-signal diffusion model that enhances data across all classes, combined with an audio-based single diffusion model to enhance rare classes. Under our data augmentation framework, higher specificity, sensitivity, and accuracy are achieved in Automatic Snoring Sound Classification (ASSC). Also, we focus on the explicitness of classification strategies, aiming to prove the enhanced data's high quality and applicability to downstream tasks. Our work provides comprehensive support for ASSC, enhancing sleep disorder diagnosis assistance offering new ideas for database research under scarce medical data conditions.
AB - Snoring can stem from various upper regions of the upper airways – the excitation location is closely linked to the unique acoustic characteristics of snore sounds, playing a vital role in sleep monitoring. The Munich-Passau Snore Sound Corpus (MPSSC) is the largest database for snoring-based auxiliary diagnosis, offering valuable data for sleep disorder research and diagnosis. However, in MPSSC, there are issues such as the small total number of samples and the uneven sample distribution. Some rare diseases have only a few case samples, failing to meet the need for sufficient learning data. To address these issues, we propose an end-to-end method for high-quality snoring audio generation for data augmentation. This method includes a Rectified-Flow-based 1D-signal diffusion model that enhances data across all classes, combined with an audio-based single diffusion model to enhance rare classes. Under our data augmentation framework, higher specificity, sensitivity, and accuracy are achieved in Automatic Snoring Sound Classification (ASSC). Also, we focus on the explicitness of classification strategies, aiming to prove the enhanced data's high quality and applicability to downstream tasks. Our work provides comprehensive support for ASSC, enhancing sleep disorder diagnosis assistance offering new ideas for database research under scarce medical data conditions.
KW - Diffusion model
KW - Flow matching
KW - Rectified flow
KW - Single data diffusion
KW - Snore sound generation
UR - https://www.scopus.com/pages/publications/105029056214
U2 - 10.1016/j.bspc.2026.109449
DO - 10.1016/j.bspc.2026.109449
M3 - Article
AN - SCOPUS:105029056214
SN - 1746-8094
VL - 116
JO - Biomedical Signal Processing and Control
JF - Biomedical Signal Processing and Control
M1 - 109449
ER -