Self-supervised speech models encode multiple speaker group attributes, with ASR finetuning discarding phonetically variant information while retaining semantically variant information.
LeBenchmark: A Reproducible Framework for Assessing Self-Supervised Representation Learning from Speech
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Speaker Group Encoding in Self-supervised Speech Recognition Models
Self-supervised speech models encode multiple speaker group attributes, with ASR finetuning discarding phonetically variant information while retaining semantically variant information.