CHSER is a new 200K-pair dataset and case study showing that fine-tuned language models can correct child ASR errors, reducing WER by up to 28.5% relative.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
eess.AS 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
CHSER: A Dataset and Case Study on Generative Speech Error Correction for Child ASR
CHSER is a new 200K-pair dataset and case study showing that fine-tuned language models can correct child ASR errors, reducing WER by up to 28.5% relative.