Adapting BERT as a text-only ASV attacker on VoicePrivacy datasets yields mean EER 35% (some speakers 2%), driven by semantic keyword overlaps from LibriSpeech curation, prompting calls to revise evaluation datasets and move beyond global EER.
Upon manual inspection, we found that the texts read by speakers 1673 and 652 were on spe- cific and unique topics, and some words recurring across their utterances
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
eess.AS 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
You Are What You Say: Exploiting Linguistic Content for VoicePrivacy Attacks
Adapting BERT as a text-only ASV attacker on VoicePrivacy datasets yields mean EER 35% (some speakers 2%), driven by semantic keyword overlaps from LibriSpeech curation, prompting calls to revise evaluation datasets and move beyond global EER.