Enhancing the Performance of Pathological Voice Quality Assessment System Through the Attention-Mechanism Based Neural Network

Han, Ji-Yan; Hsiao, Ching-Ju; Zheng, Wei-Zhong; Weng, Ko-Cheng; Ho, Guan‐Min; Chang, Chia‐Yuan; Wang, Chi‐Te; Fang, Shih-Hau; Lai, Ying‐Hui

doi:10.1016/j.jvoice.2022.12.026

Cited by 5 publications

(1 citation statement)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…AM has the advantages of solving long sequence problems, improving model performance, strong interpretability, and strong model generalization ability. AM is widely used in speech recognition, 27 image recognition, 28 fault diagnosis, 29 and other fields. Fu et al 30 added the hybrid attention module to the LeNet5 CNN.…”

Section: Introductionmentioning

confidence: 99%

Fault diagnosis of train traction motor bearing based on improved deep residual network

Sun,

He,

Lao

et al. 2023

Proceedings of the Institution of Mechanical Engineers, Part C:

View full text Add to dashboard Cite

As one of the important components of train traction motor, the bearing plays a key role in ensuring the safety of train operation. At present, the existing fault diagnosis methods for train traction motor bearings have the disadvantages of poor feature extraction ability, slow diagnosis speed, and low diagnosis accuracy. To solve the above problems, an improved deep residual network (IDRN) is proposed in this paper. Firstly, a new residual convolution block (RCB) is proposed to improve the extraction ability of hidden features. Secondly, the squeeze and excitation block (SE) is embedded in the residual block to increase the sensitivity of the model to features. Lastly, Adan is selected as the optimizer to increase the convergence speed of IDRN. The train traction motor bearing bench built by our research team is selected for the experiment. The results show that the test accuracy of IDRN on the bearing dataset of train traction motor is 98.72%, which is at least 2.27% higher than other comparative models. The IDRN model converges with fewer iterations in the training process, shortening the entire experiment time. At the same time, the CWRU bearing dataset and the bearing dataset with natural defects are selected for comparative verification. The experimental results show that the IDRN model exhibits strong robustness and practicability on different datasets.

show abstract

Section: Introductionmentioning

confidence: 99%

Fault diagnosis of train traction motor bearing based on improved deep residual network

Sun,

He,

Lao

et al. 2023

Proceedings of the Institution of Mechanical Engineers, Part C:

View full text Add to dashboard Cite

show abstract

AI Detection of Glottic Neoplasm Using Voice Signals, Demographics, and Structured Medical Records

Wang,

Chen,

Lee

et al. 2024

The Laryngoscope

View full text Add to dashboard Cite

ObjectiveThis study investigated whether artificial intelligence (AI) models combining voice signals, demographics, and structured medical records can detect glottic neoplasm from benign voice disorders.MethodsWe used a primary dataset containing 2–3 s of vowel “ah”, demographics, and 26 items of structured medical records (e.g., symptoms, comorbidity, smoking and alcohol consumption, vocal demand) from 60 patients with pathology‐proved glottic neoplasm (i.e., squamous cell carcinoma, carcinoma in situ, and dysplasia) and 1940 patients with benign voice disorders. The validation dataset comprised data from 23 patients with glottic neoplasm and 1331 patients with benign disorders. The AI model combined convolutional neural networks, gated recurrent units, and attention layers. We used 10‐fold cross‐validation (training–validation–testing: 8–1–1) and preserved the percentage between neoplasm and benign disorders in each fold.ResultsResults from the AI model using voice signals reached an area under the ROC curve (AUC) value of 0.631, and additional demographics increased this to 0.807. The highest AUC of 0.878 was achieved when combining voice, demographics, and medical records (sensitivity: 0.783, specificity: 0.816, accuracy: 0.815). External validation yielded an AUC value of 0.785 (voice plus demographics; sensitivity: 0.739, specificity: 0.745, accuracy: 0.745). Subanalysis showed that AI had higher sensitivity but lower specificity than human assessment (p < 0.01). The accuracy of AI detection with additional medical records was comparable with human assessment (82% vs. 83%, p = 0.78).ConclusionsVoice signal alone was insufficient for AI differentiation between glottic neoplasm and benign voice disorders, but additional demographics and medical records notably improved AI performance and approximated the prediction accuracy of humans.Level of EvidenceNA Laryngoscope, 2024

show abstract

Accuracy of Dysphagia Screening by Non-clinical Research Staff in the Emergency Department

Burdick,

Rogus-Pulia,

Schwei

et al. 2024

Dysphagia

View full text Add to dashboard Cite

Enhancing the Performance of Pathological Voice Quality Assessment System Through the Attention-Mechanism Based Neural Network

Cited by 5 publications

References 30 publications

Fault diagnosis of train traction motor bearing based on improved deep residual network

Fault diagnosis of train traction motor bearing based on improved deep residual network

AI Detection of Glottic Neoplasm Using Voice Signals, Demographics, and Structured Medical Records

Accuracy of Dysphagia Screening by Non-clinical Research Staff in the Emergency Department

Contact Info

Product

Resources

About