Beyond Single Ground Truth: Reference Monism as Epistemic Injustice in ASR Evaluation
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917471180554240 |
|---|---|
| author | Choi, Anna Seo Gyeong Teleki, Maria Caverlee, James del Rio, Miguel Miller, Corey Choi, Hoon |
| author_facet | Choi, Anna Seo Gyeong Teleki, Maria Caverlee, James del Rio, Miguel Miller, Corey Choi, Hoon |
| contents | Automatic speech recognition (ASR) evaluation compares system output to ground truth transcripts, with Word Error Rate (WER) quantifying the distance between them. But ground truth transcripts are not discovered - they are produced by human annotators following conventions that encode normative assumptions about which speech features matter. Different conventions (verbatim, non-verbatim, legal) produce different transcripts of identical speech and judge the same ASR output differently. This paper argues that reference monism - enforcing a single transcription convention as ground truth - commits epistemic injustice. Speakers with aphasia, whose speech includes clinically meaningful disfluencies, are systematically disadvantaged when evaluated against "clean" references that treat those disfluencies as errors. The harm is not merely differential performance, but that evaluative infrastructure lacks interpretive resources to recognize their contributions as legitimate. We develop a philosophical framework introducing the hermeneutical gap, formalize Epistemic Injustice Distance (EID) to measure reference monism's cost, and demonstrate empirically using AphasiaBank that WER varies depending on which convention defines ground truth. We propose WER-Range: reporting performance across legitimate conventions rather than assuming a single correct answer. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_07084 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Beyond Single Ground Truth: Reference Monism as Epistemic Injustice in ASR Evaluation Choi, Anna Seo Gyeong Teleki, Maria Caverlee, James del Rio, Miguel Miller, Corey Choi, Hoon Computation and Language Automatic speech recognition (ASR) evaluation compares system output to ground truth transcripts, with Word Error Rate (WER) quantifying the distance between them. But ground truth transcripts are not discovered - they are produced by human annotators following conventions that encode normative assumptions about which speech features matter. Different conventions (verbatim, non-verbatim, legal) produce different transcripts of identical speech and judge the same ASR output differently. This paper argues that reference monism - enforcing a single transcription convention as ground truth - commits epistemic injustice. Speakers with aphasia, whose speech includes clinically meaningful disfluencies, are systematically disadvantaged when evaluated against "clean" references that treat those disfluencies as errors. The harm is not merely differential performance, but that evaluative infrastructure lacks interpretive resources to recognize their contributions as legitimate. We develop a philosophical framework introducing the hermeneutical gap, formalize Epistemic Injustice Distance (EID) to measure reference monism's cost, and demonstrate empirically using AphasiaBank that WER varies depending on which convention defines ground truth. We propose WER-Range: reporting performance across legitimate conventions rather than assuming a single correct answer. |
| title | Beyond Single Ground Truth: Reference Monism as Epistemic Injustice in ASR Evaluation |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2605.07084 |