Multilingual speech foundation models, fused with a Tucker-Hadamard module, are reported to reach about 1% equal error rate on emotion fake audio detection, a large drop from prior benchmarks.
We use Fully Connected Network (FCN) and CNN as downstream networks with individual FMs
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
-
Enhancing In-Domain and Out-Domain EmoFake Detection via Cooperative Multilingual Speech Foundation Models
Multilingual speech foundation models, fused with a Tucker-Hadamard module, are reported to reach about 1% equal error rate on emotion fake audio detection, a large drop from prior benchmarks.