Pseudo-labelling and prompting with fluent transcriptions improve end-to-end spoken grammatical error correction and feedback for Whisper-based models, but the benefits depend on model size.
Increasing the model size also improves the capability of an E2E model for both SGEC and feedback tasks
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Scaling and Prompting for Improved End-to-End Spoken Grammatical Error Correction
Pseudo-labelling and prompting with fluent transcriptions improve end-to-end spoken grammatical error correction and feedback for Whisper-based models, but the benefits depend on model size.