Fact · Languages and accents
44.5Khours of English training speech
In a 2021 test of a large English speech model trained on 44.5K hours of English speech, the authors found an accuracy bias that favored the accents most prevalent in the training corpus.
Checked against its source on October 17, 2026
In the source's own words
“The model has been trained with 44.5K hours of English speech from an open access corpus called Multilingual LibriSpeech ... there is indeed an accuracy bias in terms of accentual variety, favoring the accents most prevalent in the training corpus”
English Accent Accuracy Analysis in a State-of-the-Art Automatic Speech Recognition System, Guillermo Cámbara et al., arXiv (2 pages, prepared for Phonetics and Phonology in Europe 2021), 2021, Abstract.
Open the original- What it measures
- The authors tested a model trained on Multilingual LibriSpeech against recordings of many English accents from the Common Voice corpus, and reported word error rate for each accent group.
- What it does not show
- A two-page conference paper. The abstract does not give US or UK figures, and the per-accent results are shown in a figure, so this fact does not say whether American or British accents scored higher.