Page 248 - 《应用声学》2025年第1期

244 2025 年 1 月

Proceedings of the second joint 24th annual conference [23] Ningthoujam A, Sharma R K. Classification of healthy,
and the annual fall meeting of the biomedical engineering insomnia and other pathological voice samples[C]//2020
society. IEEE, 2002: 182–183. First IEEE International Conference on Measurement,
[11] Chen L L, Chen J J. Deep neural network for automatic Instrumentation, Control and Automation (ICMICA).
classification of pathological voice signals[J]. Journal of IEEE, 2020: 1–6.
Voice, 2022, 36(2): 288. e15–288. e24. [24] Gidaye G, Nirmal J, Ezzine K, et al. Application of glot-
[12] Kadiri S R, Alku P. Analysis and detection of pathological tal flow descriptors for pathological voice diagnosis[J]. In-
voice using glottal source features[J]. IEEE Journal of Se- ternational Journal of Speech Technology, 2020, 23(1):
lected Topics in Signal Processing, 2019, 14(2): 367–379. 205–222.
[13] Belabbas S, Addou D, Selouani S A. Pathological voice [25] Di Cesare M G, Perpetuini D, Cardone D, et al. As-
classification system based on CNN-BiLSTM network us- sessment of voice disorders using machine learning and
ing speech enhancement and multi-stream approach[J]. vocal analysis of voice samples recorded through smart-
International Journal of Speech Technology, 2024, 27(2): phones[J]. BioMedInformatics, 2024, 4(1): 549–565.
483–502. [26] Sefara T J, Engelbrecht A P, Cloete I. Towards multiclass
[14] Zhao D H, Qiu Z X, Jiang Y J, et al. A depthwise separa- classification of pathological voice disorders using support
ble CNN-based interpretable feature extraction network vector machines[C]//Proceedings of the 2017 IEEE Inter-
for automatic pathological voice detection[J]. Biomedical national Conference on Computer and Information Tech-
Signal Processing and Control, 2024, 88: 105624. nology (CIT). IEEE, 2017: 1–6.
[15] Cordeiro H, Fonseca J, Guimaraes I, et al. Voice patholo- [27] Little M A, Costello D A, Harries M L. Objective dys-
gies identification speech signals, features and classi- phonia quantification in vocal fold paralysis: Comparing
fiers evaluation[C]//2015 Signal Processing: Algorithms, nonlinear, cepstral and spectral features[J]. The Journal of
Architectures, Arrangements, and Applications (SPA). the Acoustical Society of America, 2009, 126(1): 317–326.
IEEE, 2015: 81–86. [28] Chawla N V, Bowyer K W, Hall L O, et al. SMOTE:
[16] 曾晓亮, 张晓俊, 吴迪, 等. 利用声带动力学模型参数反演方 synthetic minority over-sampling technique[J]. Journal of
法进行病变嗓音分类 [J]. 声学学报, 2018, 43(1): 91–100. Artificial Intelligence Research, 2002, 16: 321–357.
Zeng Xiaoliang, Zhang Xiaojun, Wu Di, et al. Parameter [29] Elreedy D, Atiya A F, Kamalov F. A theoretical distribu-
inversion method of vocal fold dynamic model in patho- tion analysis of synthetic minority oversampling technique
logical voice classification[J]. Acta Acustica, 2018, 43(1): (SMOTE) for imbalanced learning[J]. Machine Learning,
91–100. 2024, 113(7): 4903–4923.
[17] Eye M, Infirmary E. Voice disorders database, version. [30] He H B, Bai Y, Garcia E A, et al. ADASYN: Adap-
1.03 (cd-rom)[DB/OL]. Lincoln Park, NJ: Kay Elemetrics tive synthetic sampling approach for imbalanced learn-
Corporation, 1994. ing[C]//2008 IEEE International Joint Conference on
[18] Islam R, Tarique M, Abdel-Raheem E. A survey on sig- Neural Networks (IEEE World Congress on Computa-
nal processing based pathological voice detection tech- tional Intelligence). IEEE, 2008: 1322–1328.
niques[J]. IEEE Access, 2020, 8: 66749–66776. [31] Bunkhumpornpat C, Sinapiromsaran K, Lursinsap C.
[19] Cordeiro H, Fonseca J, Guimarães I, et al. Hierar- Safe-level-smote: Safe-level-synthetic minority over-
chical classification and system combination for auto- sampling technique for handling the class imbalanced
matically identifying physiological and neuromuscular la- problem[C]//Advances in Knowledge Discovery and Data
ryngeal pathologies[J]. Journal of Voice, 2017, 31(3): Mining, 2009: 475–482.
384.e9–384.e14. [32] Bao Y, Yang S B. Two novel SMOTE methods for solving
[20] Ariyanti W, Hussain T, Wang J C, et al. Ensemble imbalanced classification problems[J]. IEEE Access, 2023,
and multimodal learning for pathological voice classifica- 11: 5816–5823.
tion[J]. IEEE Sensors Letters, 2021, 5(7): 1–4. [33] 陈丽萍, 王洪海, 何舒平. 一种基于数据分布的不平衡数据
[21] Fu D L, Zhang X H, Chen D D, et al. Pathological voice 过采样方法 [J]. 安徽大学学报 (自然科学版), 2024, 48(5):
detection based on phase reconstitution and convolutional 26–36.
neural network[J]. Journal of Voice, 2022. Chen Liping, Wang Honghai, He Shuping. An oversam-
[22] Lee J N, Lee J Y. An efficient SMOTE-based deep learning pling method for imbalanced data based on data distri-
model for voice pathology detection[J]. Applied Sciences, bution[J]. Journal of Anhui University (Natural Science
2023, 13(6): 3571. Edition), 2024, 48(5): 26–36.