VoxSafeBench reveals that speech language models recognize social norms from text but fail to apply them when acoustic cues like speaker or scene determine the appropriate response.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 2verdicts
UNVERDICTED 2roles
background 1polarities
background 1representative citing papers
A self-supervised prosody encoder with speaker disentanglement strategies outperforms raw prosody and HuBERT baselines on pitch reconstruction and prosodic event detection while achieving strong speaker separation.
citing papers explorer
-
VoxSafeBench: Not Just What Is Said, but Who, How, and Where
VoxSafeBench reveals that speech language models recognize social norms from text but fail to apply them when acoustic cues like speaker or scene determine the appropriate response.
-
Privacy-preserving Prosody Representation Learning
A self-supervised prosody encoder with speaker disentanglement strategies outperforms raw prosody and HuBERT baselines on pitch reconstruction and prosodic event detection while achieving strong speaker separation.