A Multimodal Attention Fusion-Based Model for Pathological Voice Detection
- 25 March 2026
- journal article
- Published by IOP Publishing in Biomedical Physics & Engineering Express
- Vol. 12 (2)
Abstract
Pathological voice detection provides a non-invasive and cost-effective approach for the early screening of laryngeal disorders. However, most existing methods rely on single-modal acoustic features and mainly focus on binary classification, which limits their ability to achieve fine-grained discrimination among multiple pathological voice categories. To address these limitations, this paper proposes a Multimodal Fusion Network (MFNet) with attention-based fusion for pathological voice classification. The proposed framework jointly models time-domain and frequency-domain information within a unified architecture. Specifically, SincNet is employed to extract task-relevant narrowband acoustic features directly from raw speech waveforms, while the Tunable Q-factor Wavelet Transform (TQWT) and SKNet are combined to learn multi-scale spectral representations from Mel-spectrograms. In addition, an Attentional Feature Fusion (AFF) module is introduced to adaptively integrate features from the two branches, thereby enhancing the discriminative capability of pathological voice representations. Comparative experiments on three public pathological voice datasets show that the proposed method outperforms representative baseline models and demonstrates strong robustness and generalization across different datasets. Furthermore, ablation studies further validate the effectiveness of the proposed architectural design. These results indicate that MFNet provides an effective solution for pathological voice classification and has promising potential for computer-aided voice disorder screening.Keywords
Funding Information
- National Natural Science Foundation of China (62275062)
- National Key Research and Development Program of China (2023YFC2412100)
- Shandong Province Technology Innovation Guidance Plan (YDZX2023115)
- Taishan Scholar Special Funding Project of Shandong Province
- Key Research and Development Program of Shaanxi Province (2025SF-YBXM-441)
- Shandong Laboratory of Advanced Biomaterials and Medical Devices in Weihai (ZL202402)
- Project of Shandong Innovation and Startup Community of High-end Medical Apparatus and Instruments (2023-SGTTXM-002)
- Project of Shandong Innovation and Startup Community of High-end Medical Apparatus and Instruments (2024-SGTTXM-005)
This publication has 31 references indexed in Scilit:
- Parkinson classification neural network with mass algorithm for processing speech signalsNeural Computing and Applications, 2024
- The Use of Deep Learning Software in the Detection of Voice Disorders: A Systematic ReviewOtolaryngology–Head and Neck Surgery, 2024
- MMHFNet: Multi-modal and multi-layer hybrid fusion network for voice pathology detectionExpert Systems with Applications, 2023
- Voice pathology detection using convolutional neural networks with electroglottographic (EGG) and speech signalsComputer Methods and Programs in Biomedicine Update, 2022
- Automatic spoken language identification using MFCC based time series featuresMultimedia Tools and Applications, 2022
- Gammatone spectral latitude features extraction for pathological voice detection and classificationApplied Acoustics, 2022
- Deep connected attention (DCA) ResNet for robust voice pathology detection and classificationBiomedical Signal Processing and Control, 2021
- Smart healthcare monitoring: a voice pathology detection paradigm for smart citiesMultimedia Systems, 2017
- Investigation of Voice Pathology Detection and Classification on Different Frequency Regions Using Correlation FunctionsJournal of Voice, 2017
- Voice pathology detection based on the modified voice contour and SVMBiologically Inspired Cognitive Architectures, 2016