Forensic deepfake audio detection using segmental speech features

TL;DR

This paper investigates using segmental speech features for deepfake audio detection, highlighting their interpretability and effectiveness, and proposes a speaker-specific framework suited for forensic applications.

Contribution

It introduces a novel speaker-specific deepfake detection method based on segmental speech features, contrasting with traditional speaker-independent approaches.

Findings

Segmental features improve deepfake detection accuracy.

Global features are less effective for this task.

Speaker-specific models offer forensic advantages.

Abstract

This study explores the potential of using acoustic features of segmental speech sounds to detect deepfake audio. These features are highly interpretable because of their close relationship with human articulatory processes and are expected to be more difficult for deepfake models to replicate. The results demonstrate that certain segmental features commonly used in forensic voice comparison (FVC) are effective in identifying deep-fakes, whereas some global features provide little value. These findings underscore the need to approach audio deepfake detection using methods that are distinct from those employed in traditional FVC, and offer a new perspective on leveraging segmental features for this purpose. In addition, the present study proposes a speaker-specific framework for deepfake detection, which differs fundamentally from the speaker-independent systems that dominate current benchmarks. While speaker-independent frameworks aim at broad generalization, the speaker-specific approach offers advantages in forensic contexts where case-by-case interpretability and sensitivity to individual phonetic realization are essential.