A weakly supervised Siamese CNN learns joint acoustic-phonetic word embeddings, achieving 0.95 F1 on same-word versus different-word classification with self-labeling hard-negative mining.
Multi-View Recurrent Neural Acoustic Word Embeddings
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2019 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Learning Joint Acoustic-Phonetic Word Embeddings
A weakly supervised Siamese CNN learns joint acoustic-phonetic word embeddings, achieving 0.95 F1 on same-word versus different-word classification with self-labeling hard-negative mining.