A factor-partitioned embedding framework maps speech utterances to vectors with subspaces for distinct attributes, supporting signed weighted similarity retrieval that can suppress or emphasize specific factors like speaker identity.
Deep convolutional acoustic word embeddings using word-pair side information,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
eess.AS 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Multi-Axis Speech Similarity via Factor-Partitioned Embeddings
A factor-partitioned embedding framework maps speech utterances to vectors with subspaces for distinct attributes, supporting signed weighted similarity retrieval that can suppress or emphasize specific factors like speaker identity.