An artificial intelligence-based audio recognition system for dysarthria home-based rehabilitation: A proof-of-concept study.
Source check: Source checked. Not independent scientific confirmation.
Finding: Whisper-ST1 fine-tuned from Whisper-base classifies dysarthria severity from real-world and research speech; held-out metrics and therapist agreement support a bounded proof-of-concept result.
Technology: transfer learning, progressive unfreezing and ordinal regression on TORGO plus social-media speech; held-out sample accuracy 75%, macro-F1 72%, and therapist agreement. Authors explicitly state external robustness and clinical effectiveness remain unestablished.
Publication: Peer-reviewed paper · Test context: direct test. Catalog categories, not an evidence grade.
- AI contribution
- transfer learning, progressive unfreezing and ordinal regression on TORGO plus social-media speech; held-out sample accuracy 75%, macro-F1 72%, and therapist agreement. Authors explicitly state external robustness and clinical effectiveness remain unestablished.
- Test and result
- transfer learning, progressive unfreezing and ordinal regression on TORGO plus social-media speech; held-out sample accuracy 75%, macro-F1 72%, and therapist agreement. Authors explicitly state external robustness and clinical effectiveness remain unestablished.
- Limitation / still unknown
- The reviewed source does not establish prospective benefit, broad external validity, or replication beyond the reported study.
Evidence sources and annotation context
Evidence context (descriptions follow the cited sources; test type is a catalog classification):
Evidence sources: https://journals.plos.org/digitalhealth/article?id=10.1371/journal.pdig.0001794
Source checked · editorial details
The source page was checked against this entry. Independent confirmation is not assessed by this label.
Source type: paper. Paper: not linked in this catalog; this does not mean no paper exists.
Review date: 22 Nov 2026. Review scope: Primary result-bearing material for the stated method, result and evaluation, with bibliographic version information..
No follow-up recorded; this is not a claim that no follow-up exists. Follow-up review scope and date are not recorded. No source-supported relationships recorded.
Editorial assessment: Impact 2/5 · Validation 3/5 · Novelty 2/5. Impact and novelty are editorial judgments; validation follows the annotated test type where one exists. Not an evidence grade. Scoring criteria.