Unsupervised k-means clusters of SSL features and i-vectors identify speaker-relevant feed-forward neurons; protecting them during pruning preserves speaker identification.
WavLM: Large-scale self- supervised pre-training for full stack speech process- ing
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
cs.CL 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
background 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.