Small Qwen3-ASR models fine-tuned on LLM-rewritten spoken-to-formal datasets achieve up to 37.4% relative CER reduction versus verbatim baselines while improving formal text metrics.
Connectionist temporal classifi- cation: Labelling unsegmented sequence data with re- current neural networks
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
FormalASR: End-to-End Spoken Chinese to Formal Text
Small Qwen3-ASR models fine-tuned on LLM-rewritten spoken-to-formal datasets achieve up to 37.4% relative CER reduction versus verbatim baselines while improving formal text metrics.