Unsupervised k-means clusters of SSL features and i-vectors identify speaker-relevant feed-forward neurons; protecting them during pruning preserves speaker identification.
Information-Theoretic Understanding of Population Risk Improvement with Model Com- pression
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Identifying Speaker Information in Feed-Forward Layers of Self-Supervised Speech Transformers
Unsupervised k-means clusters of SSL features and i-vectors identify speaker-relevant feed-forward neurons; protecting them during pruning preserves speaker identification.