# Detection of Cross-Dataset Fake Audio Based on Prosodic and Pronunciation Features

arXiv: https://arxiv.org/abs/2305.13700 · HTML: https://mlsanity.com/paper/2305.13700/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 23 May 2023.

## Built on by (most cited first, 10 of 10)

- [MAVOS-DD: Multilingual Audio-Video Open-Set Deepfake Detection Benchmark](https://mlsanity.com/paper/2505.11109/) (2025)
- [Prompt Tuning for Audio Deepfake Detection: Computationally Efficient Test-time Domain Adaptation with Limited Target Dataset](https://mlsanity.com/paper/2410.09869/) (2024)
- [Improving Generalization for AI-Synthesized Voice Detection](https://mlsanity.com/paper/2412.19279/) (2024)
- [Region-Based Optimization in Continual Learning for Audio Deepfake Detection](https://mlsanity.com/paper/2412.11551/) (2024)
- [Passive Deepfake Detection Across Multi-modalities: A Comprehensive Survey](https://mlsanity.com/paper/2411.17911/) (2024)
- [PhonemeFake: Redefining Deepfake Realism with Language-Driven Segmental Manipulation and Adaptive Bilevel Detection](https://mlsanity.com/paper/2506.22783/) (2025)
- [SAVe: Self-Supervised Audio-visual Deepfake Detection Exploiting Visual Artifacts and Audio-visual Misalignment](https://mlsanity.com/paper/2603.25140/) (2026)
- [AUDETER: A Large-scale Dataset for Deepfake Audio Detection in Open Worlds](https://mlsanity.com/paper/2509.04345/) (2025)
- [HuLA: Prosody-Aware Anti-Spoofing with Multi-Task Learning for Expressive and Emotional Synthetic Speech](https://mlsanity.com/paper/2509.21676/) (2025)
- [DF-MoE: Generalizable Deepfake Detection via Multimodal Sparse Mixture-of-Experts](https://mlsanity.com/paper/2608.23363/) (2026)

## Abstract (arXiv)

Existing fake audio detection systems perform well in in-domain testing, but still face many challenges in out-of-domain testing. This is due to the mismatch between the training and test data, as well as the poor generalizability of features extracted from limited views. To address this, we propose multi-view features for fake audio detection, which aim to capture more generalized features from prosodic, pronunciation, and wav2vec dimensions. Specifically, the phoneme duration features are extracted from a pre-trained model based on a large amount of speech data. For the pronunciation features, a Conformer-based phoneme recognition model is first trained, keeping the acoustic encoder part as a deeply embedded feature extractor. Furthermore, the prosodic and pronunciation features are fused with wav2vec features based on an attention mechanism to improve the generalization of fake audio detection models. Results show that the proposed approach achieves significant performance gains in several cross-dataset experiments.