A multimodal attention fusion-based model for pathological voice detection

Clinical Snapshot

Key Findings

• P Value: Not reported

• Effect Size: Not specified in abstract

• Primary Outcome: Superior classification performance compared to baseline models

• Nnt Or Sensitivity: Sensitivity and specificity values not provided

• Confidence Interval: Not reported

Clinical Application

Requires computational infrastructure and technical expertise for implementation; feasibility in routine clinical practice unclear Could complement existing ENT referral pathways and support rural/remote screening initiatives, but would require TGA approval for clinical use and integration with existing voice assessment protocols Patients requiring non-invasive screening for laryngeal disorders, particularly in primary care or specialist voice clinics

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.

References

1. 1.Li, B., Zhang, B., Huang, H., Jiang, X., Lin, C., & Sun, M. (2026). A multimodal attention fusion-based model for pathological voice detection. Biomedical Physics & Engineering Express. https://doi.org/10.1088/2057-1976/ae5713