8 papers
The Last Mile of Deepfake Speech Detection: An Industry-Academia Experience Report
Anton Firc, Kamil Malinka, Vojtěch Staněk +2
Synthetic speech detection benchmarks now report sub-1% error rates on some in-domain evaluations, yet performance degrades under unseen attacks, channel mismatch, and distribution…
VQCSim: When Does Compile-Once Statevector Simulation Beat Generic Quantum Frameworks?
Anton Firc, Martin PereÅ¡Ãni, VojtÄch Mrázek +7
Hybrid quantum-classical machine learning workflows repeatedly evaluate many small parametrized circuits during training and model exploration. In this regime, framework dispatch a…
SpAArSIST: Sparsified AASIST for Efficient and Reliable Anti-Spoofing
Anton Firc, VojtÄch StanÄk, ZbynÄk LiÄka +2
We present SpAArSIST, a deployment-oriented refinement of the widely used AASIST graph pooling backend for self-supervised learning (SSL) based anti-spoofing. Motivated by redundan…
The Hidden Cost of Pairwise Verification in Synthetic Speech Source Tracing
Anton Firc, ZbynÄk LiÄka, VojtÄch StanÄk +1
Open-set source tracing is increasingly framed as a verification problem, motivating the use of pairwise metric-learning objectives from biometrics. We thus compare global anchorin…
What Do Deepfake Speech Detectors Actually Hear?
VojtÄch StanÄk, Veronika Jirmusová, Anton Firc +3
Deepfake speech detectors often output a single score without explaining why an audio sample is flagged, where in the signal the evidence lies, or what cues drive the decision. We…
Ethical and Technical Limits of Deepfake Speech Datasets
VojtÄch StanÄk, Eva Trnovská, Kamil Malinka +1
Claims about the robustness and fairness of deepfake speech detectors are only as credible as the datasets used to train and evaluate those systems. We present a dataset-level audi…