Few-Shot Speech Deepfake Detection Adaptation with Gaussian Processes

2025/05/29 by Neta Glazer, Glazer, Neta, David Chernin +7 · 1 citation
Computer Science · #Audio and Speech Processing (eess.AS) #FOS: Computer and information sciences #FOS: Electrical engineering #Generative Adversarial Networks and Image Synthesis #Machine Learning (cs.LG) #Sound (cs.SD) #Speech Recognition and Synthesis #Speech and Audio Processing #electronic engineering #information engineering

paper · pdf · doi:10.48550/arxiv.2505.23619

openalex publication_date 2025/05/29 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

Recent advancements in Text-to-Speech (TTS) models, particularly in voice cloning, have intensified the demand for adaptable and efficient deepfake detection methods. As TTS systems continue to evolve, detection models must be able to efficiently adapt to previously unseen generation models with minimal data. This paper introduces ADD-GP, a few-shot adaptive framework based on a Gaussian Process (GP) classifier for Audio Deepfake Detection (ADD). We show how the combination of a powerful deep embedding model with the Gaussian processes flexibility can achieve strong performance and adaptability. Additionally, we show this approach can also be used for personalized detection, with greater robustness to new TTS models and one-shot adaptability. To support our evaluation, a benchmark dataset is constructed for this task using new state-of-the-art voice cloning models.

Citations

• F5-TTS: A Fairytaler that Fakes Fluent and Faithful Speech with Flow Matching
• Cross-Domain Audio Deepfake Detection: Dataset and Analysis
• What to Remember: Self-Adaptive Continual Learning for Audio Deepfake Detection
• Audio Deepfake Detection: A Survey
• Voicebox: Text-Guided Multilingual Universal Speech Generation at Scale
• Speak Foreign Languages with Your Own Voice: Cross-Lingual Neural Codec Language Modeling
• Guided Deep Kernel Learning
• Speak, Read and Prompt: High-Fidelity Text-to-Speech with Minimal Supervision
• Neural Codec Language Models are Zero-Shot Text to Speech Synthesizers
• Pushing the limits of raw waveform speaker recognition
• Automatic speaker verification spoofing and deepfake detection using wav2vec 2.0 and data augmentation
• XLS-R: Self-supervised Cross-lingual Speech Representation Learning at Scale
• AASIST: Audio Anti-Spoofing using Integrated Spectro-Temporal Graph Attention Networks
• End-to-End Spectro-Temporal Graph Attention Networks for Speaker Verification Anti-Spoofing and Speech Deepfake Detection
• Personalized Federated Learning with Gaussian Processes
• LoRA: Low-Rank Adaptation of Large Language Models
• HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Units
• GP-Tree: A Gaussian Process Classifier for Few-Shot Incremental Learning
• Multi-Class Gaussian Process Classification Made Conjugate: Efficient Inference via Data Augmentation
• Dirichlet-based Gaussian Processes for Large-scale Calibrated Classification
• mixup: Beyond Empirical Risk Minimization
• Stochastic Variational Deep Kernel Learning
• Deep Kernel Learning
• Scalable Variational Gaussian Process Classification
• Manifold Gaussian Processes for Regression
• Bayesian inference for logistic models using Polya-Gamma latent variables
• Bayesian Inference for Logistic Models Using Pólya–Gamma Latent Variables
• Where are we in audio deepfake detection? A systematic analysis over generative and detection models

Cited by

• CompSpoof: A Dataset and Joint Learning Framework for Component-Level Audio Anti-spoofing Countermeasures

Related

• Cross-Domain Audio Deepfake Detection: Dataset and Analysis
• A robust audio deepfake detection system via multi-view feature
• SLIM: Style-Linguistics Mismatch Model for Generalized Audio Deepfake Detection
• Unmasking Deepfakes: Leveraging Augmentations and Features Variability for Deepfake Speech Detection
• Generalizable Detection of Audio Deepfakes