Speech-based depression detection models primarily learn speaker identity rather than depression biomarkers, with performance dropping sharply on unseen speakers even under adversarial training.
To simulate these under controlled condi- tions, we use the size-matched split described in Section 2.2, yielding two training sets and a shared test set
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
eess.AS 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Who is Speaking or Who is Depressed? A Controlled Study of Speaker Leakage in Speech-Based Depression Detection
Speech-based depression detection models primarily learn speaker identity rather than depression biomarkers, with performance dropping sharply on unseen speakers even under adversarial training.