๐Ÿ“–
A corpus-only AUC diagnostic for pooled speech-based depression detection
Cezary Polak, Milosz Dudek, Daria Hemmerling

A corpus-only AUC diagnostic for pooled speech-based depression detection

Science & Mathematics Published 2026 Verification Pending

Overview & Synopsis

When clinical speech corpora are pooled for evaluation, corpus membership can itself become predictive if class prevalences differ across sources. We derive the AUC of an oracle predictor that uses only corpus identity and empirical prevalence, a diagnostic computable directly from corpus composition. Across five depression corpora in three languages (590 speakers), the corpus-only AUC is 0.697, and corpus identity is predicted from six acoustic and self-supervised representations with 97.5-99.8% accuracy. Permuting depression labels within each corpus removes label structure while preserving prevalences; the residual pooled-minus-LOCO discrepancy then increases across three nested configurations in the same order as the diagnostic. Pooled 5-fold cross-validation also outscores corpus-held-out evaluation across all six representations. Prevalence equalisation substantially reduces the discrepancy for eGeMAPS and WavLM-Base, whereas a sample-size-matched control does not. Corpus-specific base rates therefore create a measurable shortcut opportunity in pooled clinical-speech evaluation, motivating corpus-aware diagnostics alongside pooled performance.

Indexed from repository: arXiv (arxiv.org)
Loading document from verified source...
Keyboard Shortcuts: ← / → for pages • + / - for zoom • 0 to fit width Powered by Mozilla PDF.js v3.11

Document Information

Document Title A corpus-only AUC diagnostic for pooled speech-based depression detection
Author / Organization Cezary Polak, Milosz Dudek, Daria Hemmerling
Subject & Discipline eess.AS
Categories Science & Mathematics
Publication Year 2026
License / Rights arXiv Open Access / Creative Commons
Resource Verification Listed PDF (Verification Pending)
Original Host Website arXiv (arxiv.org)
File Format application/pdf (Portable Document Format)
Language EN
Catalog ID DOC-264235
Original Source Link Visit Source Page on arxiv.org »