Deep connected attention (DCA) ResNet for robust voice pathology detection and classification. (September 2021)

• Record Type: Journal Article
• Authors: Ding, Huijun; Gu, Zixiong; Dai, Peng; Zhou, Zhou; Wang, Lu; Wu, Xiaoxiao
• Is Part Of: Biomedical signal processing and control. Volume 70(2021)
• Publication Date: 2021-09
• Subjects: Voice pathology -- Automatic detection -- Convolutional neural network -- Deep learning; Signal processing -- Periodicals; Biomedical engineering -- Periodicals; Signal Processing, Computer-Assisted -- Periodicals; Image Processing, Computer-Assisted -- Periodicals; Biomedical Engineering -- Periodicals; 610.28
• DOI: 10.1016/j.bspc.2021.102973
• Languages: English
• ISSNs: 1746-8094

Abstract

Abstract: The automatic diagnosis method based on speech signal analysis is able to realize the detection and classification of pathological voices. It plays an important role in the early diagnosis and auxiliary treatment of voice pathology, which effectively relief the discomfort of patients and reduce the workload of doctors. Therefore, the automatic diagnosis method based on speech signal analysis is of great research value. Meanwhile, high accuracy, high precision and stability are the pursuit goals. In this paper, a novel computer-aided assessment based on speech signal analysis for pathological voice classification (CS-PVC) system is proposed. This model focuses on the areas with large differences between different pathological voices and healthy voices, while ignore the negative impact of insignificant information on the performance of the model. Two databases were used in the experiments, one is the Saarbruecken Voice database (SVD), and the other is the self-built Shenzhen People's Hospital voice database (SZUPD). The pathological voice detection accuracy of the proposed system on the above two databases are 81.6% and 82.2% respectively. The experimental results show that the proposed framework is not data-dependence. In other words, it has the potential to be universally applicable in medical framework in the future. Highlights: A voice-based non-invasive voice disease detection method is proposed. The MFSC together with its derivatives are used as acoustic features. A novel Deep connected attention model (DCA-ResNet) is proposed as the classifier. Prove the generalization of the algorithm on multiple data sets.