SpeechDx: A Multi-Task Benchmark for Clinical Speech AI
Quick Answer
SpeechDx introduces a comprehensive benchmark for clinical speech AI, encompassing 12 datasets and 27 tasks across various health conditions.
Quick Take
It evaluates generalization in clinical speech models, revealing that large-scale models outperform domain-specific ones, yet no current model generalizes effectively across the clinical spectrum.
Key Points
- SpeechDx spans 12 datasets and 27 tasks related to clinical speech AI.
- Tasks are structured by stages of speech production: conceptualization, formulation, and articulation.
- Large-scale speech models provide the strongest baselines in performance evaluations.
- Domain-specific models only enhance performance on closely matched tasks.
- No current model reliably generalizes across diverse clinical speech conditions.
Paper Resources
Source Excerpt
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. …
Want this in your inbox every morning?
Daily brief at your local 8am — bilingual EN/中文, free.
More from arXiv cs.AI
See more →HOBA: Hierarchical On-Policy Bidding Agents for Adaptive Online Advertising
HOBA (Hierarchical On-policy Bidding Agents) is a novel hierarchical reinforcement learning framework that enhances online advertising bidding systems by improving adaptability and reducing hyperparameter tuning costs. It utilizes a for hyperparameter inference, a SARSA agent for expert model selection, and a dynamic expert pool for bid execution, achieving a +3.6% increase in target cost during large-scale deployment and outperforming state-of-the-art baselines on AuctionNet.