Peer-reviewed research
Speech Errors on Frequently Observed Homophones in French: Perceptual Evaluation vs Automatic Classification
Rena Nemoto et al., Proceedings of LREC 2008, 2008
Read the originalRead on October 17, 2026
- What it is
- Nemoto, Vasilescu and Adda-Decker studied speech recognition errors on French homophones, especially et (and) and est (is). They compared the errors with the results of a listening test by human transcribers.
- How much weight it carries
- Peer-reviewed LREC paper from a speech laboratory. It is a 2008 study of an older recognizer and tests only a few word pairs, so it shows the kind of error rather than current accuracy.
Facts taken from this source
- Nemoto and colleagues studied the French homophones et (and) and est (is), which speech recognizers separate mainly with language model weights.
“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” (Abstract)