J-j-j-just Stutter: Benchmarking Whisper's Performance Disparities on Different Stuttering Patterns
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?
Accessibility datasets are often annotated by crowdworkers without disability-specific expertise.
“accessibility datasets are often annotated by crowdworkers without disability-specific expertise, leading to inconsistent or inaccurate labels.”
From Disability-First AI Dataset Annotation: Co-designing Stuttered Speech Annotation Guidelines with People Who Stutter (2026) · cites this paper as [92]
Annotation by crowdworkers without disability-specific expertise leads to inconsistent or inaccurate labels in accessibility datasets.
“leading to inconsistent or inaccurate labels.”
From Disability-First AI Dataset Annotation: Co-designing Stuttered Speech Annotation Guidelines with People Who Stutter (2026) · cites this paper as [92]
Similar label inconsistencies have been observed in datasets of sign languages and stuttered speech.
“Similar label inconsistencies have been observed in datasets of sign languages [12] and stuttered speech [58, 92].”
From Disability-First AI Dataset Annotation: Co-designing Stuttered Speech Annotation Guidelines with People Who Stutter (2026) · cites this paper as [92]
A recent study by PWS researchers observed a significant number of mistakes in the original event labels of Sep-28k and adjusted the labeling for over 25% of the 2,621 clips in their sample.
“a recent study conducted by a team of PWS researchers (Sridhar and Wu) observed a significant number of 'mistakes' in the original event labels and adjusted the labeling for over 25% of the 2,621 clips in their sample for their benchmarking studies [92].”
From Disability-First AI Dataset Annotation: Co-designing Stuttered Speech Annotation Guidelines with People Who Stutter (2026) · cites this paper as [92]
The work by Sridhar and Wu calls into question the original labels of Sep-28k.
“Their work calls into question the original labels of Sep-28k and yields a re-annotated subset”
From Disability-First AI Dataset Annotation: Co-designing Stuttered Speech Annotation Guidelines with People Who Stutter (2026) · cites this paper as [92]
We focused on Sep-28k due to its widespread use, its public availability of annotations produced by PWS and non-PWS, and the reported discrepancy between these two versions.
“We focused on Sep-28k due to its widespread use 4 , its public availability of annotations produced by PWS [92] and non-PWS [58], and the reported discrepancy between these two versions [92].”
From Disability-First AI Dataset Annotation: Co-designing Stuttered Speech Annotation Guidelines with People Who Stutter (2026) · cites this paper as [92]
The present study was directly motivated by labeling issues identified in existing stuttered speech datasets.
“The present study was directly motivated by labeling issues identified in existing stuttered speech datasets [57, 92].”
From Disability-First AI Dataset Annotation: Co-designing Stuttered Speech Annotation Guidelines with People Who Stutter (2026) · cites this paper as [92]
Our analysis reveals substantial annotation disagreements between Sep-28k and Sep-28k-SW.
“In line with Sridhar and Wu's findings [92], our analysis reveals substantial annotation disagreements between Sep-28k and Sep28k-SW.”
From Disability-First AI Dataset Annotation: Co-designing Stuttered Speech Annotation Guidelines with People Who Stutter (2026) · cites this paper as [92]
Cites
Still being checked.
Cited by
Sorted by citations
Tang, X., Li, J., & Wu, S. (2026) · Proceedings of the 2026 CHI Conference on Human Factors in Computing Systems · doi:10.1145/3772318.3790405 · Cited by 4 · see citing works
“The present study was directly motivated by labeling issues identified in existing stuttered speech datasets [57, 92].”
InfluentialSelf-citationSohrabi, R. (2026) · AI & Society · doi:10.1007/s00146-026-03073-y
- Authors
- Sridhar, C., & Wu, S.
- ORCID
- Wu, Shaomei
- Venue
- Interspeech 2025
- Publisher
- ISCA
- Published
- 2025-08-17
- Pages
- 3753-3757
- ISSN
- 2308-457X (ISSN-L)
- OpenAlex
- W4415432776
- Cited by
- 1
- References
- 0
- Citations by year
- 2026: 1
- FWCI
- 0.95
- Type
- conference paper
- Language
- en
- Open access
- closed
- Locations
- Interspeech (USB) (publishedVersion)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Speech Recognition and Synthesis
- Social Sciences › Psychology › Clinical Psychology › Stuttering Research and Treatment
- Physical Sciences › Computer Science › Computer Networks and Communications › Software System Performance and Reliability
- Keywords
- stuttering, Whisper, speech synthesis, benchmarking
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
