VoiceMark embeds watermarks in speaker-specific codec latents and detects them with over 95% accuracy after zero-shot voice cloning, versus about 50% for prior methods.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.SD 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
VoiceMark: Zero-Shot Voice Cloning-Resistant Watermarking Approach Leveraging Speaker-Specific Latents
VoiceMark embeds watermarks in speaker-specific codec latents and detects them with over 95% accuracy after zero-shot voice cloning, versus about 50% for prior methods.