FlanEC maps five-candidate ASR lists to corrected transcripts and gets its best average word error rate (8.5%) from a 3B Flan-T5 model trained on all HyPoradise domains with full fine-tuning.
In Automatic Speech Recognition (ASR) systems, GenSEC acts as an effective post-processing step to enhance the accuracy [1, 2]
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
support 1representative citing papers
citing papers explorer
-
FlanEC: Exploring Flan-T5 for Post-ASR Error Correction
FlanEC maps five-candidate ASR lists to corrected transcripts and gets its best average word error rate (8.5%) from a 3B Flan-T5 model trained on all HyPoradise domains with full fine-tuning.