A simple bottom-up prominence-based segmenter matches a top-down clustering-refined system on ZeroSpeech word discovery while being about five times faster, and both are limited mainly by K-means clustering of averaged HuBERT embeddings.
Computational modeling of phonetic and lexical learning in early language acquisition: Existing models and future directions,
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
eess.AS 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
Should Top-Down Clustering Affect Boundaries in Unsupervised Word Discovery?
A simple bottom-up prominence-based segmenter matches a top-down clustering-refined system on ZeroSpeech word discovery while being about five times faster, and both are limited mainly by K-means clustering of averaged HuBERT embeddings.