Mitigating Scoring Errors and Compensating for Nonverbal Subtests in Speech-Based Dementia Assessment
For clinicians and researchers in dementia assessment, this work offers a speech-based method to improve accessibility and reduce subjectivity, though it is an incremental improvement over existing automated scoring approaches.
This study develops speech-based models for the German Syndrom-Kurz-Test that integrate transcript-derived scores and Whisper embeddings to reduce scoring errors and approximate expert overall ratings even when motor subtests are omitted, achieving strong correlation with expert ratings and accurate discrimination between cognitive status groups.
Early detection of cognitive impairment relies on neuropsychological tests to minimize subjectivity by assessing multiple cognitive domains. Speech-based evaluation can support diagnostics and improve accessibility, but transcription errors and the omission of nonverbal subtests (e.g., motor skills) limit accuracy. Beyond conventional test scores, speech-derived features can provide additional insights into cognitive status. This study investigates the speech-based evaluation of the German "Syndrom-Kurz-Test," a standardized dementia screening test comprising verbal and motor subtests. We train models that integrate transcript-derived scores and Whisper embeddings per verbal subtest to reduce scoring errors. To compensate for missing motor subtests, we then leverage these fused representations to approximate expert overall ratings. Despite omitting subtests, our models strongly correlate with expert ratings and efficiently and accurately discriminate between cognitive status groups.