DarkStream combines a causal content encoder with limited lookahead, k-means quantization, and a GAN-based pseudo-speaker embedding to anonymize speech in real time with near-chance speaker-verification error rates.
Hifi-gan: Generative adversarial networks for efficient and high fidelity speech synthesis,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
eess.AS 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
DarkStream: real-time speech anonymization with low latency
DarkStream combines a causal content encoder with limited lookahead, k-means quantization, and a GAN-based pseudo-speaker embedding to anonymize speech in real time with near-chance speaker-verification error rates.