Fact · Languages and accents
2.7percent word error rate
The same best English speech recognition model, tested by the EdAcc authors on US English clean read speech, had a word error rate of 2.7 percent.
Checked against its source on October 17, 2026
In the source's own words
“obtains an average of 19.7% word error rate (WER) -- in contrast to the 2.7% WER obtained when evaluated on US English clean read speech.”
The Edinburgh International Accents of English Corpus: Towards the Democratization of English ASR, Ramon Sanabria et al., arXiv (accepted to IEEE ICASSP 2023), 2023, Abstract.
Open the original- What it measures
- The authors use this US clean read speech result as the reference point for the accented conversational speech in EdAcc.
- What it does not show
- Read speech from one accent is much easier than conversation from many accents, so this baseline shows the size of the gap between the two test conditions, not the effect of accent alone.