Fact · Languages and accents
Nemoto and colleagues studied the French homophones et (and) and est (is), which speech recognizers separate mainly with language model weights.
Checked against its source on October 17, 2026
In the source's own words
“A first question of interest is whether homophone words such as et, (and) and est (to be), for which ASR systems rely on language model weights”
Speech Errors on Frequently Observed Homophones in French: Perceptual Evaluation vs Automatic Classification, Rena Nemoto et al., Proceedings of LREC 2008, 2008, Abstract.
Open the original- What it measures
- The study compared automatic errors with a listening test. Human listeners used local context more efficiently than the recognizer in their conditions.
- What it does not show
- A 2008 study with a small set of word pairs. Modern French dictation is far more accurate overall, but the same homophone pairs remain the hard cases.