aiqbench analysis
This research presents a novel machine learning approach to disentangling depression signals from cognitive decline in elderly speech, demonstrating that formant features are the primary acoustic markers when controlling for mild cognitive impairment. By utilizing concurrent clinical assessments, the study identifies interpretable patterns that outperform standard baselines and self-supervised representations, offering a more accurate diagnostic tool for co-occurring affective and cognitive conditions.
Disentangling Depression from Cognitive Decline in Elderly Speech Using Concurrent Clinical Assessments
arXiv:2610.26890v1 Announce Type: cross Abstract: Detecting depression from speech in elderly patients with mild cognitive impairment (MCI) is complicated by overlapping acoustic effects of cognitive decline. Without disentangling these, classifiers risk learning cognitive rather than depression-specific patterns. We present a Korean elderly speech corpus of 89 MCI speakers collected over three years with concurrent depression (SGDS) and cognitive (MMSE) assessments. Both linear mixed-effects models and partial correlations identify the same pattern: of seven feature groups, only formant features are associated with depression after controlling for cognitive function, while widely used F0 features carry no signal. The F1+F2 subset achieves UAR 0.760 with just 12 features, outperforming both the full eGeMAPS baseline and self-supervised representations. These findings show that concurrent clinical assessments can identify interpretable, depression-specific acoustic markers in populations where cognitive and affective symptoms co-occur.
Abstract:Detecting depression from speech in elderly patients with mild cognitive impairment (MCI) is complicated by overlapping acoustic effects of cognitive decline. Without disentangling these, classifiers risk learning cognitive rather than depression-specific patterns. We present a Korean elderly speech corpus of 89 MCI speakers collected over three years with concurrent depression (SGDS) and cognitive (MMSE) assessments. Both linear mixed-effects models and partial correlations identify the same pattern: of seven feature groups, only formant features are associated with depression after controlling for cognitive function, while widely used F0 features carry no signal. The F1+F2 subset achieves UAR 0.760 with just 12 features, outperforming both the full eGeMAPS baseline and self-supervised representations. These findings show that concurrent clinical assessments can identify interpretable, depression-specific acoustic markers in populations where cognitive and affective symptoms co-occur.
Audio and Speech Processing (eess.AS); Artificial Intelligence (cs.AI); Computation and Language (cs.CL); Sound (cs.SD)
arXiv:2610.26890 [eess.AS]
(or arXiv:2610.26890v1 [eess.AS] for this version)
https://doi.org/10.48550/arXiv.2610.26890 Focus to learn more arXiv-issued DOI via DataCite
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Full text under the publisher's open licence · 233 words
Related coverage
Clifford disentanglers for entanglement reduction in molecular electronic structure simulations
arXiv · Jun 11, 2026
Polar: LLM-Powered Synthesis of Real-World Cyber Evidence for Prioritization and Mitigation
arXiv · Oct 7, 2026
Researchers Bound Entanglement Using Best Separable Approximation
Quantum Zeitgeist · Aug 24, 2026
X-MULTI: VLM-based Imaging Factor Disentanglement for Factor-Aware Image Synthesis
arXiv · Aug 26, 2026