# Quantification of stylistic differences in human- and ASR-produced transcripts of African American English

arXiv: https://arxiv.org/abs/2409.03059 · HTML: https://mlsanity.com/paper/2409.03059/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 3 of its 21 references that are in the map.
- First posted on arXiv 4 Sep 2024.

## Builds on (most cited first, 3 of 3)

- [Robust Speech Recognition via Large-Scale Weak Supervision](https://mlsanity.com/paper/2212.04356/) (2022)
- [Earnings-21: A Practical Benchmark for ASR in the Wild](https://mlsanity.com/paper/2104.11348/) (2021)
- [Improving Contextual Recognition of Rare Words with an Alternate Spelling Prediction Model](https://mlsanity.com/paper/2209.01250/) (2022)

## Built on by (most cited first, 2 of 2)

- [Towards Orthographically-Informed Evaluation of Speech Recognition Systems for Indian Languages](https://mlsanity.com/paper/2603.00941/) (2026)
- [Transcription Policy as a Latent Variable: Activating Controllable Verbatim ASR with Word-Level Timing](https://mlsanity.com/paper/2607.18934/) (2026)

## Abstract (arXiv)

Common measures of accuracy used to assess the performance of automatic speech recognition (ASR) systems, as well as human transcribers, conflate multiple sources of error. Stylistic differences, such as verbatim vs non-verbatim, can play a significant role in ASR performance evaluation when differences exist between training and test datasets. The problem is compounded for speech from underrepresented varieties, where the speech to orthography mapping is not as standardized. We categorize the kinds of stylistic differences between 6 transcription versions, 4 human- and 2 ASR-produced, of 10 hours of African American English (AAE) speech. Focusing on verbatim features and AAE morphosyntactic features, we investigate the interactions of these categories with how well transcripts can be compared via word error rate (WER). The results, and overall analysis, help clarify how ASR outputs are a function of the decisions made by the training data's human transcribers.