# Heterogeneity over Homogeneity: Investigating Multilingual Speech Pre-Trained Models for Detecting Audio Deepfake

arXiv: https://arxiv.org/abs/2404.00809 · HTML: https://mlsanity.com/paper/2404.00809/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 31 Mar 2024.

## Built on by (most cited first, 14 of 14)

- [The Codecfake Dataset and Countermeasures for the Universally Detection of Deepfake Audio](https://mlsanity.com/paper/2405.04880/) (2024)
- [Detect All-Type Deepfake Audio: Wavelet Prompt Tuning for Enhanced Auditory Perception](https://mlsanity.com/paper/2504.06753/) (2025)
- [Multilingual Source Tracing of Speech Deepfakes: A First Benchmark](https://mlsanity.com/paper/2508.04143/) (2025)
- [Tell me Habibi, is it Real or Fake?](https://mlsanity.com/paper/2505.22581/) (2025)
- [Interpretable All-Type Audio Deepfake Detection with Audio LLMs via Frequency-Time Reinforcement Learning](https://mlsanity.com/paper/2601.02983/) (2026)
- [Multi-level SSL Feature Gating for Audio Deepfake Detection](https://mlsanity.com/paper/2509.03409/) (2025)
- [AT-ADD: All-Type Audio Deepfake Detection Challenge Evaluation Plan](https://mlsanity.com/paper/2604.08184/) (2026)
- [Melody or Machine: Detecting Synthetic Music with Dual-Stream Contrastive Learning](https://mlsanity.com/paper/2512.00621/) (2025)
- [Investigating the Viability of Employing Multi-modal Large Language Models in the Context of Audio Deepfake Detection](https://mlsanity.com/paper/2601.00777/) (2026)
- [Are Music Foundation Models Better at Singing Voice Deepfake Detection? Far-Better Fuse them with Speech Foundation Models](https://mlsanity.com/paper/2409.14131/) (2024)
- [PARROT: Synergizing Mamba and Attention-based SSL Pre-Trained Models via Parallel Branch Hadamard Optimal Transport for Speech Emotion Recognition](https://mlsanity.com/paper/2506.01138/) (2025)
- [Are Mamba-based Audio Foundation Models the Best Fit for Non-Verbal Emotion Recognition?](https://mlsanity.com/paper/2506.02258/) (2025)
- [Whilter: A Whisper-based Data Filter for "In-the-Wild" Speech Corpora Using Utterance-level Multi-Task Classification](https://mlsanity.com/paper/2507.21642/) (2025)
- [Revealing the Truth with ConLLM for Detecting Multi-Modal Deepfakes](https://mlsanity.com/paper/2601.17530/) (2026)

## Abstract (arXiv)

In this work, we investigate multilingual speech Pre-Trained models (PTMs) for Audio deepfake detection (ADD). We hypothesize that multilingual PTMs trained on large-scale diverse multilingual data gain knowledge about diverse pitches, accents, and tones, during their pre-training phase and making them more robust to variations. As a result, they will be more effective for detecting audio deepfakes. To validate our hypothesis, we extract representations from state-of-the-art (SOTA) PTMs including monolingual, multilingual as well as PTMs trained for speaker and emotion recognition, and evaluated them on ASVSpoof 2019 (ASV), In-the-Wild (ITW), and DECRO benchmark databases. We show that representations from multilingual PTMs, with simple downstream networks, attain the best performance for ADD compared to other PTM representations, which validates our hypothesis. We also explore the possibility of fusion of selected PTM representations for further improvements in ADD, and we propose a framework, MiO (Merge into One) for this purpose. With MiO, we achieve SOTA performance on ASV and ITW and comparable performance on DECRO with current SOTA works.