Enforcing one transcription convention as ground truth in ASR commits epistemic injustice against speakers with aphasia, as shown by varying WER on AphasiaBank data, leading to the proposal of WER-Range across legitimate conventions.
R., Jurafsky, D., and Goel, S.Racial disparities in automated speech recognition.Proceedings of the national academy of sciences 117, 14 (2020), 7684–7689
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Beyond Single Ground Truth: Reference Monism as Epistemic Injustice in ASR Evaluation
Enforcing one transcription convention as ground truth in ASR commits epistemic injustice against speakers with aphasia, as shown by varying WER on AphasiaBank data, leading to the proposal of WER-Range across legitimate conventions.