SpeechDx: A Multi-Task Benchmark for Clinical Speech AI

Researchers introduced SpeechDx, a large-scale benchmark for clinical speech AI spanning 12 datasets and 27 tasks across diverse health conditions, designed to evaluate generalization by structuring tasks according to disrupted speech production stages. Testing 12 state-of-the-art audio encoders revealed that large-scale speech models provide the strongest baselines, but no current representation generalizes reliably across all clinical speech tasks, highlighting the need for a shared evaluation framework.

arXiv:2606.17339v1 Announce Type: new Abstract: Speech offers a uniquely informative window into health by simultaneously engaging neurological, motor, respiratory, and vocal systems. Current clinical speech AI methods have largely progressed through isolated condition-specific studies, making results difficult to compare and generalization difficult to assess. We introduce SpeechDx, a large-scale benchmark for clinical speech AI spanning 12 datasets and 27 tasks across diverse health conditions. To enable evaluation across shared clinical mechanisms, SpeechDx structures tasks by the stage of speech production they disrupt: conceptualization, formulation, and articulation. The benchmark tests generalization by including tasks with limited labeled data and evaluating the same health condition across multiple datasets, distinguishing clinically meaningful patterns from dataset artefacts. We systematically evaluate 12 state-of-the-art audio encoders across all tasks and under zero-shot cross-condition transfer. Results show that large-scale speech models represent the strongest overall baselines, domain-specific models improve performance only on closely matched tasks, and no current representation generalizes reliably across the clinical speech landscape. SpeechDx establishes a shared evaluation framework for tracking progress toward general-purpose clinical speech representations