The first multilingual source-tracing benchmark for speech deepfakes, showing LFCC-ECAPA-TDNN generalizes best across languages.
Promptvc: Flexible stylistic voice conversion in latent space driven by natural language prompts,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
eess.AS 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
Multilingual Source Tracing of Speech Deepfakes: A First Benchmark
The first multilingual source-tracing benchmark for speech deepfakes, showing LFCC-ECAPA-TDNN generalizes best across languages.