GM-OT, a fused Wasserstein and Gromov-Wasserstein graph-matching alignment for BERT-to-acoustic knowledge transfer, reports 3.98% CER on AISHELL-1 test versus 5.76% for a Conformer+CTC baseline.
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
-
Cross-modal Knowledge Transfer Learning as Graph Matching Based on Optimal Transport for ASR
GM-OT, a fused Wasserstein and Gromov-Wasserstein graph-matching alignment for BERT-to-acoustic knowledge transfer, reports 3.98% CER on AISHELL-1 test versus 5.76% for a Conformer+CTC baseline.