BanglaFake: Constructing and Evaluating a Specialized Bengali Deepfake Audio Dataset
Not on the map. Why?
Abstract (arXiv)
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.
Key facts. Cited by 1 paper in the map (data through 13 Oct 2026). Builds on 17 of its 25 references that are in the map. First posted on arXiv 16 May 2025.
Builds on
17 of 25 references.
References · 17
- 2020wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representationscited by 3,870
- 2019Common Voice: A Massively-Multilingual Speech Corpuscited by 1,366
- 2020HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesiscited by 1,148
- 2019An Introduction to Variational Autoencoderscited by 998
- 2023Neural Codec Language Models are Zero-Shot Text to Speech Synthesizerscited by 745
- 2021Conditional Variational Autoencoder with Adversarial Learning for End-to-End Text-to-Speechcited by 559
- 2020Glow-TTS: A Generative Flow for Text-to-Speech via Monotonic Alignment Searchcited by 272
- 2019Flow++: Improving Flow-Based Generative Models with Variational Dequantization and Architecture Designcited by 260
- 2021FakeAVCeleb: A Novel Audio-Video Multimodal Deepfake Datasetcited by 180
- 2021ASVspoof 2021: accelerating progress in spoofed and deepfake speech detectioncited by 158
- 2023ADD 2023: the Second Audio Deepfake Detection Challengecited by 64
- 2023ZMM-TTS: Zero-shot Multilingual and Multispeaker Speech Synthesis Conditioned on Self-supervised Discrete Speech Representationscited by 15
5 more
- 2024LiveSpeech: Low-Latency Zero-shot Text-to-Speech via Autoregressive Modeling of Audio Discrete Codescited by 13
- 2021An Introduction to Variational Inferencecited by 11
- 2023Learning to Speak from Text: Zero-Shot Multilingual Text-to-Speech with Unsupervised Text Pretrainingcited by 10
- 2020Exploring Gaussian mixture model framework for speaker adaptation of deep neural network acoustic modelscited by 1
- 2023Comparative Analysis of Transfer Learning in Deep Learning Text-to-Speech Models on a Few-Shot, Low-Resource, Customized Datasetcited by 1
Built on by
Citing papers per year: 2025: 1.
1 paper.