Voice Disorder

Voice disorder research aims to develop accurate and efficient automated diagnostic tools for various laryngeal pathologies, improving early detection and treatment. Current research heavily utilizes deep learning models, such as transformers, convolutional neural networks, and recurrent neural networks, often incorporating techniques like multi-level feature fusion and canonical correlation analysis to enhance classification performance and address challenges posed by noisy or limited datasets. This work is significant because it offers the potential for non-invasive, accessible, and objective voice disorder assessment, ultimately improving patient care and reducing the burden on healthcare systems.