Court-Admissible Audio Authentication Platform for AI-Generated Speech Detection (CA3P)

• Unité de recherche: INNOSUISSE
• Numéro de projet: 136.282 IP-ICT
• Titre du projet anglais: Court-Admissible Audio Authentication Platform for AI-Generated Speech Detection (CA3P)

Mots-clé (Anglais)

ICT, Deep learning

Résumé des résultats (Abstract) (Anglais)

Deepfake detection is technically mature but legally unusable: no current system explains why audio is classified as synthetic. This project delivers forensic-grade explainability and reproducible benchmarks, unlocking adoption in forensics, law enforcement, and finance.