APA
Click to copy
Wang, Y., Wang, F., Huang, G., Zheng, X., Lei, B., & Yuan, X. (2026). Spectral-Trustworthy Augmentation Harmonizer Toward Automated Lung Auscultation Under Pathological Sample-Scarcity Scenario. IEEE Transactions on Audio, Speech and Language Processing, 34, 2007–2020. https://doi.org/10.1109/TASLPRO.2026.3678800
Chicago/Turabian
Click to copy
Wang, Ying, Fan Wang, Guoheng Huang, Xiaobin Zheng, Baiying Lei, and Xiaochen Yuan. “Spectral-Trustworthy Augmentation Harmonizer Toward Automated Lung Auscultation Under Pathological Sample-Scarcity Scenario.” IEEE Transactions on Audio, Speech and Language Processing 34 (2026): 2007–2020.
MLA
Click to copy
Wang, Ying, et al. “Spectral-Trustworthy Augmentation Harmonizer Toward Automated Lung Auscultation Under Pathological Sample-Scarcity Scenario.” IEEE Transactions on Audio, Speech and Language Processing, vol. 34, 2026, pp. 2007–20, doi:10.1109/TASLPRO.2026.3678800.
BibTeX Click to copy
@article{wang2026a,
title = {Spectral-Trustworthy Augmentation Harmonizer Toward Automated Lung Auscultation Under Pathological Sample-Scarcity Scenario},
year = {2026},
journal = {IEEE Transactions on Audio, Speech and Language Processing},
pages = {2007-2020},
volume = {34},
doi = {10.1109/TASLPRO.2026.3678800},
author = {Wang, Ying and Wang, Fan and Huang, Guoheng and Zheng, Xiaobin and Lei, Baiying and Yuan, Xiaochen}
}
Abstract：Despite the limited availability of pathological samples, automated lung auscultation continues to strive to establish a reliable diagnostic model. Due to this scarcity, existing automated classification methods focus primarily on feature augmentation and transfer learning, while overlooking the challenges of data quality control during the augmentation process and domain adaptation. To address these challenges, we propose a Spectral-Trustworthy Augmentation Harmonizer (STAH) framework comprising three synergistic components. First, SpecDiver (SD) generates a balanced and expanded data distribution via multi-level resampling and quantization augmentation. Based on this expanded spectral domain, TrustworthyAugFilter (TAF) then employs a dual-branch propagation mechanism with confidence-guided filtering to retain beneficial augmented samples while eliminating harmful ones that could destabilize training. Linking the SD and TAF components, HarmonicBridge (HaB) transfers representational knowledge from natural images to the spectral domain through innovative frequency decomposition, recombination, and reconstruction processes. Tests on the SPRSound 2022 dataset show that STAH gets scores of 91.02%, 79.38%, and 69.87% for tasks 1-1, 2-1, and 2-2. In the 2023 version of the dataset, our STAH reaches 82.47%, 80.46%, and 73.02% for these same tasks. We also tested our method using the ICBHI 2017 dataset. It achieves an Average Score of 73.52% for the binary task and 66.11% for the four-class task.