Are reported accuracies in the clinical speech machine learning literature overoptimistic?
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
Not having enough data for system training may likely result in an algorithm with poor external validity to speakers it has never seen before (overfitting).
“Not having enough data for system training may likely result in an algorithm with poor external validity to speakers it has never seen before, a machine learning problem known as overfitting (Berisha et al., 2022).”
From Equipping Speech-Language Clinicians for the Critical Appraisal of an Artificial Intelligence–Driven, Evidence-Based Future (2025) · cites this paper as Berisha et al., 2022
Maximum performance speech tasks are particularly suitable for clinical AI because the context is meant to maximally tax the speech system every time.
“For these reasons, maximum performance speech tasks (Kent et al., 1987) are particularly suitable for clinical AI because the context is meant to maximally tax the speech system every time (Berisha et al., 2022).”
From Equipping Speech-Language Clinicians for the Critical Appraisal of an Artificial Intelligence–Driven, Evidence-Based Future (2025) · cites this paper as Berisha et al., 2022
Cited by
Sorted by citations
Speech based detection of Alzheimer's disease: a survey of AI techniques, datasets and challenges
Ding, K., Chetty, M., Noori Hoshyar, A., Bhattacharya, T., & Klein, B. (2024) · Artificial Intelligence Review · doi:10.1007/s10462-024-10961-6 · Cited by 82 · see citing works
Berisha, V., & Liss, J. M. (2024) · npj Digital Medicine · doi:10.1038/s41746-024-01199-1 · Cited by 41 · see citing works
Self-citationBenway, N. R., & Preston, J. L. (2025) · Language, Speech, and Hearing Services in Schools · doi:10.1044/2025_lshss-24-00085 · Cited by 12 · see citing works
- Authors
- Berisha, V., Krantsevich, C., Stegmann, G., Hahn, S., & Liss, J.
- Venue
- Interspeech 2022
- Publisher
- ISCA
- Published
- 2022-09-18
- Pages
- 2453-2457
- ISSN
- 2308-457X (ISSN-L)
- OpenAlex
- W4297841370
- Cited by
- 27
- References
- 0
- Citations by year
- 2026: 2 · 2025: 5 · 2024: 12 · 2023: 8
- FWCI
- 3.46
- Type
- conference paper
- Language
- en
- Open access
- closed
- Locations
- Interspeech (USB) (publishedVersion)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Speech Recognition and Synthesis
- Health Sciences › Medicine › Physiology › Voice and Speech Disorders
- Health Sciences › Health Professions › Health Information Management › Artificial Intelligence in Healthcare
- Keywords
- overoptimism, evaluation benchmark
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
