Source Verification for Speech Deepfakes

Authors: Viola Negroni, Davide Salvi, Paolo Bestagini, Stefano Tubaro

Published: 2025-05-20 10:42:48+00:00

AI Summary

This paper introduces the novel task of source verification for speech deepfakes, focusing on determining if a test audio track originates from the same generative model as a set of reference tracks. The approach leverages embeddings from a classifier trained for source attribution, comparing embeddings using cosine similarity to assess source identity.

Abstract

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 attribution models attempt to address this challenge, they often struggle in open-set conditions against unseen generators. In this paper, we introduce the source verification task, which, inspired by speaker verification, determines whether a test track was produced using the same model as a set of reference signals. Our approach leverages embeddings from a classifier trained for source attribution, computing distance scores between tracks to assess whether they originate from the same source. We evaluate multiple models across diverse scenarios, analyzing the impact of speaker diversity, language mismatch, and post-processing operations. This work provides the first exploration of source verification, highlighting its potential and vulnerabilities, and offers insights for real-world forensic applications.