8 papers
Forensic Similarity for Speech Deepfakes
Viola Negroni, Davide Salvi, Daniele Ugo Leonzio +2
In this paper, we introduce the concept of forensic similarity in the speech deepfake detection domain, which aims to determine whether two audio segments share the same underlying…
Not All Deepfakes Are Created Equal: Triaging Audio Forgeries for Robust Deepfake Singer Identification
Davide Salvi, Hendrik Vincent Koops, Elio Quinton
The proliferation of highly realistic singing voice deepfakes presents a significant challenge to protecting artist likeness and content authenticity. Automatic singer identificati…
Attention-based Mixture of Experts for Robust Speech Deepfake Detection
Viola Negroni, Davide Salvi, Alessandro Ilic Mezza +2
AI-generated speech is becoming increasingly used in everyday life, powering virtual assistants, accessibility tools, and other applications. However, it is also being exploited fo…
Phoneme-Level Analysis for Person-of-Interest Speech Deepfake Detection
Davide Salvi, Viola Negroni, Sara Mandelli +2
Recent advances in generative AI have made the creation of speech deepfakes widely accessible, posing serious challenges to digital trust. To counter this, various speech deepfake…
Source Verification for Speech Deepfakes
Viola Negroni, Davide Salvi, Paolo Bestagini +1
With the proliferation of speech deepfake generators, it becomes crucial not only to assess the authenticity of synthetic audio but also to trace its origin. While source attributi…
Anomaly Detection and Localization for Speech Deepfakes via Feature Pyramid Matching
Emma Coletta, Davide Salvi, Viola Negroni +2
The rise of AI-driven generative models has enabled the creation of highly realistic speech deepfakes - synthetic audio signals that can imitate target speakers' voices - raising c…