SCDF: A Speaker Characteristics DeepFake Speech Dataset for Bias Analysis
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866918122130243584 |
|---|---|
| author | Staněk, Vojtěch Srna, Karel Firc, Anton Malinka, Kamil |
| author_facet | Staněk, Vojtěch Srna, Karel Firc, Anton Malinka, Kamil |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2508_07944 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | SCDF: A Speaker Characteristics DeepFake Speech Dataset for Bias Analysis Staněk, Vojtěch Srna, Karel Firc, Anton Malinka, Kamil Sound Artificial Intelligence Cryptography and Security 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. |
| title | SCDF: A Speaker Characteristics DeepFake Speech Dataset for Bias Analysis |
| topic | Sound Artificial Intelligence Cryptography and Security |
| url | https://arxiv.org/abs/2508.07944 |