A fused self-supervised encoder and learned DP decoder for word alignment outperforms MFA on English datasets and generalizes to unseen languages.
The IFA corpus: A phonemically segmented Dutch open source speech database,
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
-
Multilingual Word-Level Forced Alignment with Self-Supervised Representations and Learned Dynamic Programming
A fused self-supervised encoder and learned DP decoder for word alignment outperforms MFA on English datasets and generalizes to unseen languages.