Multi-Backbone Self-Supervised Ensembles for Audio Deepfake Detection and a Cross-Track Analysis of Generation-Detection Asymmetry
Seunghyun Kim, Junghyun Kim, Jiyoung Woo
cs.SD, cs.CR
Submitted: 2026-08-03
Comments: Accepted at CLEF 2026, ImageCLEF-Deepfake task. Published in CEUR-WS CLEF 2026 Working Notes
Code: https://github.com/spotify/pedalboard
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- ASVspoof 5: Crowdsourced Speech Data, Deepfakes, and Adversarial Attacks at Scale
- WavLM model ensemble for audio deepfake detection
- Improving Out-of-Domain Audio Deepfake Detection via Layer Selection and Fusion of SSL-Based Countermeasures
- ALLM4ADD: Unlocking the Capabilities of Audio Large Language Models for Audio Deepfake Detection
- HoliAntiSpoof: Audio LLM for Holistic Speech Anti-Spoofing
- Audio Deepfake Detection in the Age of Advanced Text-to-Speech models
- WavLM: Large-Scale Self-Supervised Pre-Training for Full Stack Speech Processing
- HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Units
- XLS-R: Self-supervised Cross-lingual Speech Representation Learning at Scale
- End-to-end anti-spoofing with RawNet2
- AASIST: Audio Anti-Spoofing using Integrated Spectro-Temporal Graph Attention Networks
- F5-TTS: A Fairytaler that Fakes Fluent and Faithful Speech with Flow Matching
- XTTS: a Massively Multilingual Zero-Shot Text-to-Speech Model
- CosyVoice: A Scalable Multilingual Zero-shot Text-to-speech Synthesizer based on Supervised Semantic Tokens
- Robust Speech Recognition via Large-Scale Weak Supervision
- ECAPA-TDNN: Emphasized Channel Attention, Propagation and Aggregation in TDNN Based Speaker Verification
- SpeechBrain: A General-Purpose Speech Toolkit
- Does Audio Deepfake Detection Generalize?
- Perturbed Public Voices (P$^{2}$V): A Dataset for Robust Audio Deepfake Detection
- VoiceWukong: Benchmarking Deepfake Voice Detection
Related papers
- Few-Shot Open-Set Audio Classification via Transductive Prototype Refinement and Class Logit Enhancement
- Spectral Masking and Interpolation Attack (SMIA): A Black-box Adversarial Attack against Voice Authentication and Anti-Spoofing Systems
- Remix the Timbre: Diffusion-Based Style Transfer Across Polyphonic Stems
- Harmonic Representations in Symbolic Music Transformers are Localized and Controllable
- AVMeme Exam: A Multimodal Multilingual Multicultural Benchmark for LLMs' Contextual and Cultural Knowledge and Thinking
- SoundWeaver: Compositional Warm-Starting for Text-to-Audio Diffusion Serving