End-to-end Whisper models, trained with 2,500 hours of pseudo-labeled speech, fluent prompts, aligned references, and confidence filtering, outperform cascaded systems on spoken grammatical error correction and feedback.
On assessing and developing spoken ’grammatical error correction’ systems,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
End-to-End Spoken Grammatical Error Correction
End-to-end Whisper models, trained with 2,500 hours of pseudo-labeled speech, fluent prompts, aligned references, and confidence filtering, outperform cascaded systems on spoken grammatical error correction and feedback.