AuralGuard: Multi-View One-Class Learning for Generalizable and Calibrated Detection of AI-Generated Speech in the Wild
Official checkpoint repository and benchmark artifacts for the paper:
"AuralGuard: Multi-View One-Class Learning for Generalizable and Calibrated Detection of AI-Generated Speech in the Wild"
Target: Elsevier Computer Speech & Language / IEEE Transactions on Information Forensics and Security (IEEE TIFS)
- 📄 Camera-Ready Manuscript (17 Pages): paper/main.pdf
- 💻 Official Code Repository: github.com/MIHMahmudEli/auralguardv2
- 👥 Authors: Mohsin Ibna Hossain, Md. Muttakin, Sadman Hasan Miraj, and Mohammad Mahmudul Hasan (Corresponding Author)
- 🏛️ Affiliation: Department of Computer Science, American International University-Bangladesh (AIUB)
📊 Empirical Benchmark Results
Trained strictly once on ASVspoof 2019 LA and evaluated zero-shot out-of-domain across all benchmarks. Metrics report point estimates with 95% non-parametric bootstrap confidence intervals ($B=1,000$).
| Architecture | In-Domain (19LA) EER (%) | min t-DCF | Zero-Shot (In-the-Wild) EER (%) | ITW AUROC | ITW ECE (↓) | Zero-Shot (WaveFake) EER (%) |
|---|---|---|---|---|---|---|
| B1 (LFCC-LCNN) | 16.29 [15.97, 16.63] | 0.6131 | 50.62 [49.72, 51.49] | 0.4979 | 0.4292 | 45.32 [44.82, 45.82] |
| B2 (RawNet2) | 8.99 [8.72, 9.23] | 0.3444 | 38.08 [37.28, 38.89] | 0.6671 | 0.5761 | 50.37 [49.88, 50.88] |
| B3 (AASIST) | 10.63 [10.36, 10.92] | 0.3921 | 42.33 [41.52, 43.14] | 0.6122 | 0.5552 | 49.89 [49.39, 50.39] |
| B5 (WavLM+OCS) | 2.86 [2.73, 3.00] | 0.1041 | 16.55 [16.12, 16.98] | 0.9103 | 0.2320 | 47.43 [46.93, 47.93] |
| AuralGuard (v1) | 7.30 [7.12, 7.50] | 0.2494 | 23.47 [23.03, 23.89] | 0.8345 | 0.0965 | 48.72 [48.22, 49.22] |
| AuralGuard v2 | 6.81 [6.61, 7.00] | 0.2398 | 19.19 [18.78, 19.61] | 0.8820 | 0.1716 | 45.19 [44.69, 45.71] |
📈 Actual Manuscript Figures
1. Cross-Domain Generalization (Fig. 6)
2. Detection Error Tradeoff (DET) Curves (Fig. 7)
3. Non-Parametric 95% Bootstrap Confidence Intervals (Fig. 8)
4. Discrimination vs. Probability Calibration (Fig. 9)
5. Out-of-Domain Reliability Diagram on In-the-Wild (Fig. 10)
📦 Checkpoint Directory
| Model | Path in Repo | Description |
|---|---|---|
| AuralGuard v2 | checkpoints/auralguard_v2/best.ckpt |
Multi-view + Gated Cross-Attention + AASIST + OCS + SupCon |
| AuralGuard (v1) | checkpoints/auralguard/best.ckpt |
Multi-view + AASIST + OCS |
| B5 (WavLM+OCS) | checkpoints/b5_wavlm_ocs/best.ckpt |
Single-view WavLM-Large + AASIST + OCS |
| B3 (AASIST) | checkpoints/b3_aasist/best.ckpt |
Sinc-conv raw waveform + Graph attention network |
| B2 (RawNet2) | checkpoints/b2_rawnet2/best.ckpt |
Sinc-conv raw waveform + residual blocks + GRU |
| B1 (LFCC-LCNN) | checkpoints/b1_lcnn/best.ckpt |
60-dim LFCC + Max-Feature-Map CNN |
🚀 Quick Usage
from huggingface_hub import hf_hub_download
import torch
# Download AuralGuard v2 checkpoint
ckpt_path = hf_hub_download(
repo_id="MoshinAli/auralguard-checkpoints",
filename="checkpoints/auralguard_v2/best.ckpt"
)
print(f"Downloaded checkpoint to: {ckpt_path}")