BanglaFake: Constructing and Evaluating a Specialized Bengali Deepfake Audio Dataset
Fuente:
arXiv
Salvato in:
| Autori principali: | , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866909612282740736 |
|---|---|
| author | Fahad, Istiaq Ahmed Asif, Kamruzzaman Sikder, Sifat |
| author_facet | Fahad, Istiaq Ahmed Asif, Kamruzzaman Sikder, Sifat |
| contents | Deepfake audio detection is challenging for low-resource languages like Bengali due to limited datasets and subtle acoustic features. To address this, we introduce BangalFake, a Bengali Deepfake Audio Dataset with 12,260 real and 13,260 deepfake utterances. Synthetic speech is generated using SOTA Text-to-Speech (TTS) models, ensuring high naturalness and quality. We evaluate the dataset through both qualitative and quantitative analyses. Mean Opinion Score (MOS) from 30 native speakers shows Robust-MOS of 3.40 (naturalness) and 4.01 (intelligibility). t-SNE visualization of MFCCs highlights real vs. fake differentiation challenges. This dataset serves as a crucial resource for advancing deepfake detection in Bengali, addressing the limitations of low-resource language research. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_10885 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | BanglaFake: Constructing and Evaluating a Specialized Bengali Deepfake Audio Dataset Fahad, Istiaq Ahmed Asif, Kamruzzaman Sikder, Sifat Sound Artificial Intelligence Audio and Speech Processing Deepfake audio detection is challenging for low-resource languages like Bengali due to limited datasets and subtle acoustic features. To address this, we introduce BangalFake, a Bengali Deepfake Audio Dataset with 12,260 real and 13,260 deepfake utterances. Synthetic speech is generated using SOTA Text-to-Speech (TTS) models, ensuring high naturalness and quality. We evaluate the dataset through both qualitative and quantitative analyses. Mean Opinion Score (MOS) from 30 native speakers shows Robust-MOS of 3.40 (naturalness) and 4.01 (intelligibility). t-SNE visualization of MFCCs highlights real vs. fake differentiation challenges. This dataset serves as a crucial resource for advancing deepfake detection in Bengali, addressing the limitations of low-resource language research. |
| title | BanglaFake: Constructing and Evaluating a Specialized Bengali Deepfake Audio Dataset |
| topic | Sound Artificial Intelligence Audio and Speech Processing |
| url | https://arxiv.org/abs/2505.10885 |