Pathological Voice Feature Generation Using Generative Adversarial Network

Qian, Jinyang; Denghuang, Zhao; Fan, Ziqi; Wu, Di; Xu, Yishen; Tao, Zhi

doi:10.1109/icsmd53520.2021.9670757

Cited by 2 publications

(1 citation statement)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Besides, some studies have added auxiliary inputs, for example, medical records [41] and the GRBAS scale [42], to help classify pathological voices. Based on the promising performance under ideal conditions, Hsu et al [43] further addressed the channel effect due to hardware variation; Fan et al [44] and Jinyang et al [45] investigated the sample imbalance between voice disorders. With the development of the Internet of Things (IoT), IoT and cloud technology has also been applied to voice pathology monitoring [46]- [49].…”

Section: Introductionmentioning

confidence: 99%

Toward Real-World Voice Disorder Classification

Kuo

Hsieh

Tseng

et al. 2023

IEEE Trans. Biomed. Eng.

View full text Add to dashboard Cite

Objective: Voice disorders significantly compromise individuals' ability to speak in their daily lives. Without early diagnosis and treatment, these disorders may deteriorate drastically. Thus, automatic classification systems at home are desirable for people who are inaccessible to clinical disease assessments. However, the performance of such systems may be weakened due to the constrained resources and domain mismatch between the clinical data and noisy real-world data. Methods: This study develops a compact and domain-robust voice disorder classification system to identify the utterances of health, neoplasm, and benign structural diseases. Our proposed system utilizes a feature extractor model composed of factorized convolutional neural networks and subsequently deploys domain adversarial training to reconcile the domain mismatch by extracting domain-invariant features. Results: The results show that the unweighted average recall in the noisy realworld domain improved by 13% and remained at 80% in the clinic domain with only slight degradation. The domain mismatch was effectively eliminated. Moreover, the proposed system reduced the usage of both memory and computation by over 73.9%. Conclusion: By deploying factorized convolutional neural networks and domain adversarial training, domain-invariant features can be derived for voice disorder classification with limited resources. The promising results confirm that the proposed system can significantly reduce resource consumption and improve classification accuracy by considering the domain mismatch. Significance: To the best of our knowledge, this is the first study that jointly considers real-world model compression and noise-robustness issues in voice disorder classification. The proposed system is intended for application to embedded systems with limited resources.

show abstract

Section: Introductionmentioning

confidence: 99%

Toward Real-World Voice Disorder Classification

Kuo

Hsieh

Tseng

et al. 2023

IEEE Trans. Biomed. Eng.

View full text Add to dashboard Cite

show abstract

An Efficient SMOTE-Based Deep Learning Model for Voice Pathology Detection

Lee

2023

Applied Sciences

View full text Add to dashboard Cite

The Saarbruecken Voice Database (SVD) is a public database used by voice pathology detection systems. However, the distributions of the pathological and normal voice samples show a clear class imbalance. This study aims to develop a system for the classification of pathological and normal voices that uses efficient deep learning models based on various oversampling methods, such as the adaptive synthetic sampling (ADASYN), synthetic minority oversampling technique (SMOTE), and Borderline-SMOTE directly applied to feature parameters. The suggested combinations of oversampled linear predictive coefficients (LPCs), mel-frequency cepstral coefficients (MFCCs), and deep learning methods can efficiently classify pathological and normal voices. The balanced datasets from ADASYN, SMOTE, and Borderline-SMOTE are used to validate and evaluate the various deep learning models. The experiments are conducted using model evaluation metrics such as the recall, specificity, G, and F1 value. The experimental results suggest that the proposed voice pathology detection (VPD) system integrating the LPCs oversampled by the SMOTE and a convolutional neural network (CNN) can effectively yield the highest accuracy at 98.89% when classifying pathological and normal voices. Finally, the performances of oversampling algorithms such as the ADASYN, SMOTE, and Borderline-SMOTE are discussed. Furthermore, the performance of SMOTE is superior to conventional imbalanced data oversampling algorithms, and it can be used to diagnose pathological signals in real-world applications.

show abstract

Pathological Voice Feature Generation Using Generative Adversarial Network

Cited by 2 publications

References 15 publications

Toward Real-World Voice Disorder Classification

Toward Real-World Voice Disorder Classification

An Efficient SMOTE-Based Deep Learning Model for Voice Pathology Detection

Contact Info

Product

Resources

About