SCDF: A Speaker Characteristics DeepFake Speech Dataset for Bias Analysis
This addresses bias and fairness issues in deepfake speech detection for researchers and developers, though it is incremental as it focuses on dataset creation and evaluation rather than a new detection method.
The authors tackled the problem of bias in deepfake speech detection by introducing the SCDF dataset, which contains over 237,000 utterances across five languages and diverse speaker characteristics, and they found that speaker characteristics significantly influence detection performance with disparities across sex, language, age, and synthesizer type.
Despite growing attention to deepfake speech detection, the aspects of bias and fairness remain underexplored in the speech domain. To address this gap, we introduce the Speaker Characteristics Deepfake (SCDF) dataset: a novel, richly annotated resource enabling systematic evaluation of demographic biases in deepfake speech detection. SCDF contains over 237,000 utterances in a balanced representation of both male and female speakers spanning five languages and a wide age range. We evaluate several state-of-the-art detectors and show that speaker characteristics significantly influence detection performance, revealing disparities across sex, language, age, and synthesizer type. These findings highlight the need for bias-aware development and provide a foundation for building non-discriminatory deepfake detection systems aligned with ethical and regulatory standards.