VocalAgent: Large Language Models for Vocal Health Diagnostics with Safety-Aware Evaluation
This addresses the problem of limited access to convenient vocal health diagnostics for people with voice disorders, though it appears incremental as it applies an existing LLM method to a new domain.
The paper tackles vocal health diagnosis by introducing VocalAgent, an audio large language model fine-tuned on hospital patient datasets, which achieves superior accuracy in voice disorder classification compared to state-of-the-art baselines.
Vocal health plays a crucial role in peoples' lives, significantly impacting their communicative abilities and interactions. However, despite the global prevalence of voice disorders, many lack access to convenient diagnosis and treatment. This paper introduces VocalAgent, an audio large language model (LLM) to address these challenges through vocal health diagnosis. We leverage Qwen-Audio-Chat fine-tuned on three datasets collected in-situ from hospital patients, and present a multifaceted evaluation framework encompassing a safety assessment to mitigate diagnostic biases, cross-lingual performance analysis, and modality ablation studies. VocalAgent demonstrates superior accuracy on voice disorder classification compared to state-of-the-art baselines. Its LLM-based method offers a scalable solution for broader adoption of health diagnostics, while underscoring the importance of ethical and technical validation.