Spooftral: Can Voxtral Audio-Language Model Detect Speech Spoofing?

arXiv:2609.28713 · eess.AS, cs.CL · Submitted 2026-09-23 · Read on arXiv

eess.AS, cs.CL

Submitted: 2026-09-23

Updated: 2026-09-23

Comments: 8 pages, 3 figures, 5 tables. Accepted to the Spoken Language Technology (SLT) 2026

Code: https://github.com/avishai111/Spooftral

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Verification — 17× in this paper · explained in 2 episodes
• Adaptation — 16× in this paper · explained in 1 episode
• Embeddings — 9× in this paper · explained in 2 episodes
• Generalization — 6× in this paper · explained in 13 episodes
• Linear Probing — 5× in this paper · explained in 2 episodes
• Regularization — 5× in this paper · explained in 3 episodes
• Fine-Tuning — 4× in this paper · explained in 5 episodes
• Alignment — 3× in this paper · explained in 1 episode
• Data Augmentation — 3× in this paper · explained in 7 episodes
• Robustness — 3× in this paper · explained in 5 episodes
• Self-Supervised Learning — 3× in this paper · explained in 7 episodes
• Self-Supervised Learning (SSL) — 2× in this paper · explained in 4 episodes
• Ablation — 1× in this paper · explained in 1 episode
• Activation Function — 1× in this paper · explained in 1 episode
• AdamW Optimizer — 1× in this paper · explained in 1 episode
• Adversarial Attacks — 1× in this paper · explained in 1 episode
• Anti-Spoofing Systems — 1× in this paper · explained in 2 episodes
• Automatic Speech Recognition (ASR) — 1× in this paper · explained in 2 episodes
• Benchmark — 1× in this paper · explained in 2 episodes
• Benchmarking — 1× in this paper · explained in 3 episodes
• Interpretability — 1× in this paper · explained in 15 episodes
• Low-Rank Adaptation (LoRA) — 1× in this paper · explained in 9 episodes
• Multi-Agent System — 1× in this paper · explained in 5 episodes
• Quantization — 1× in this paper · explained in 12 episodes
• Transferability — 1× in this paper · explained in 4 episodes
• Transformer — 1× in this paper · explained in 2 episodes
• Two-Stage Framework — 1× in this paper · explained in 2 episodes
• Unified Framework — 1× in this paper · explained in 5 episodes

Sources

• A Survey of Threats Against Voice Authentication and Anti-Spoofing Systems
• Does Audio Deepfake Detection Generalize?
• Tandem spoofing-robust automatic speaker verification based on time-domain embeddings
• Improving Out-of-Domain Audio Deepfake Detection via Layer Selection and Fusion of SSL-Based Countermeasures
• Automatic speaker verification spoofing and deepfake detection using wav2vec 2.0 and data augmentation
• Audio-CoT: Exploring Chain-of-Thought Reasoning in Large Audio Language Model
• SpeechGPT: Empowering Large Language Models with Intrinsic Cross-Modal Conversational Abilities
• SALMONN: Towards Generic Hearing Abilities for Large Language Models
• Qwen-Audio: Advancing Universal Audio Understanding via Unified Large-Scale Audio-Language Models
• Voxtral
• Audio-Language Models for Audio-Centric Tasks: A Systematic Survey
• Direct Language Model Alignment from Online AI Feedback
• Voxtral Realtime
• Ministral 3
• A Study of BFLOAT16 for Deep Learning Training
• StarGANv2-VC: A Diverse, Unsupervised, Non-parallel Framework for Natural-Sounding Voice Conversion

Related papers

• Rethinking Entropy Allocation in LLM-based ASR: Understanding the Dynamics between Speech Encoders and LLMs
• X-VC: Zero-shot Streaming Voice Conversion in Codec Space
• Autoregressive Guidance of Deep Spatially Selective Filters using Bayesian Tracking for Efficient Extraction of Moving Speakers
• VM-ARRAYDPS: Virtual Microphone Augmented Diffusion Posterior Sampling for Unsupervised Blind Speech Separation
• Conditional Flow Matching for Visually-Guided Acoustic Highlighting
• Anonymization, Not Elimination: Utility-Preserved Speech Anonymization