notesum.ai
Published at November 21Single-Model Attribution for Spoofed Speech via Vocoder Fingerprints in an Open-World Setting
eess.AS
cs.CR
Released Date: November 21, 2024
Authors: Matías Pizarro1, Mike Laszkiewicz1, Dorothea Kolossa2, Asja Fischer1
Aff.: 1Faculty of Computer Science, Ruhr University Bochum, Germany; 2Electronic Systems of Medical Engineering, Technische Universität Berlin, Germany

| Mel-G | PWG | MB-MG | MG-L | FB-MG | HF-G | WGlow | Avo | BVG | BVG-L | Real | Avg. | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Mel-G | - | 1.00/1.00 | 1.00/1.00 | 0.88/1.00 | 1.00/1.00 | 1.00/1.00 | 1.00/1.00 | 1.00/1.00 | 1.00/1.00 | 1.00/1.00 | 1.00/1.00 | 0.99/1.00 |
| PWG | 1.00/1.00 | - | 0.96/1.00 | 1.00/1.00 | 0.97/1.00 | 1.00/1.00 | 0.99/1.00 | 0.97/1.00 | 0.98/1.00 | 0.99/1.00 | 0.99/1.00 | 0.99/1.00 |
| MB-MG | 1.00/1.00 | 0.99/1.00 | - | 1.00/1.00 | 0.85/1.00 | 1.00/1.00 | 1.00/1.00 | 0.96/1.00 | 0.98/1.00 | 0.99/1.00 | 0.95/1.00 | 0.97/1.00 |
| MG-L | 0.94/1.00 | 1.00/1.00 | 1.00/1.00 | - | 1.00/1.00 | 1.00/1.00 | 1.00/1.00 | 1.00/1.00 | 1.00/1.00 | 1.00/1.00 | 1.00/1.00 | 0.99/1.00 |
| FB-MG | 1.00/0.99 | 0.99/0.98 | 0.82/0.95 | 1.00/0.99 | - | 1.00/1.00 | 1.00/1.00 | 0.93/0.99 | 0.97/0.99 | 0.98/1.00 | 0.93/0.95 | 0.96/0.99 |
| HF-G | 1.00/1.00 | 0.99/1.00 | 1.00/1.00 | 1.00/1.00 | 1.00/1.00 | - | 0.98/1.00 | 1.00/1.00 | 1.00/1.00 | 1.00/1.00 | 1.00/1.00 | 1.00/1.00 |
| WGlow | 1.00/1.00 | 0.98/1.00 | 0.99/1.00 | 1.00/1.00 | 0.99/1.00 | 0.99/1.00 | - | 0.99/1.00 | 0.98/1.00 | 1.00/1.00 | 1.00/1.00 | 0.99/1.00 |
| Avo | 1.00/1.00 | 0.98/1.00 | 0.91/1.00 | 1.00/1.00 | 0.84/0.99 | 1.00/1.00 | 1.00/1.00 | - | 0.97/1.00 | 0.99/1.00 | 0.97/1.00 | 0.97/1.00 |
| BVG | 1.00/1.00 | 1.00/0.99 | 0.98/1.00 | 1.00/1.00 | 0.97/1.00 | 1.00/1.00 | 1.00/1.00 | 0.99/1.00 | - | 0.96/0.99 | 0.99/1.00 | 0.99/1.00 |
| BVG-L | 1.00/1.00 | 1.00/1.00 | 0.98/1.00 | 1.00/1.00 | 0.96/1.00 | 1.00/1.00 | 1.00/1.00 | 0.99/1.00 | 0.94/1.00 | - | 0.98/1.00 | 0.99/1.00 |