Abstract
Neurological voice disorders, such as Parkinson's disease, laryngeal dystonia, and stroke-induced dysarthria, significantly impact speech production and communication. Traditional diagnostic methods rely on subjective assessment, whereas artificial intelligence (AI) offers objective, noninvasive, and scalable solutions for voice analysis. This review examines the applications, advancements, challenges, and future prospects of AI-driven methods in diagnosing, monitoring, and treating neurological voice disorders. We analyze recent advances in AI-based voice analysis, including machine learning, deep learning and signal processing techniques, and evaluate their effectiveness based on existing literature. AI models have demonstrated high accuracy in detecting subtle voice impairments, enabling early diagnosis of voice disorders, and predicting treatment response. Deep learning methods, particularly convolutional and transformer-based networks, have been effective in extracting meaningful biomarkers from acoustic or other modality data. Despite these promising advances, challenges remain, including limited high-quality data sets on some rare neurological voice disorders, ethical concerns regarding patient privacy, and the need for broad clinical validation. Further research should focus on developing standardized data sets, improving the ability of the AI model to learn representations, and enhancing its generalizability. With further development, AI-driven data analysis has the potential to transform the early detection and management of neurological voice disorders.