Latest Research in Sound
43 research papers · 2026 median publication year
Top Research Topics in Sound
- Sound — 24 papers
- Audio and Speech Processing — 8 papers
- Speech Recognition and Synthesis — 5 papers
- Cryptography and Security — 3 papers
- Memory Processes and Influences — 2 papers
- Speech and Audio Processing — 1 papers
Highest-Cited Papers
- Vauxguard: Zero-Shot LLM-Mediated Interpretable Acoustic Forensics for Synthetic Speech Detection
- Vauxguard: Zero-Shot LLM-Mediated Interpretable Acoustic Forensics for Synthetic Speech Detection
- Reconstruction history, not synthesis: benign processing moves frozen detectors on genuine human speech
- A geometry-aware deep learning framework for detecting diffusion-era synthetic speech in digital security applications
- Reconstruction history, not synthesis: benign processing moves frozen detectors on genuine human speech
- CoRELoop: Parameter-Efficient Controlled Recurrent Refinement for Audio Deepfake Detection
- Robust Workflow Generation via Adversarial Learning for Audio Deepfake Detection
- ML-ITW: A Multilingual in-the-wild Benchmark for Speech Deepfake Detection
- Language Orthogonalization for Zero-Shot Cross-Lingual Audio Deepfake Detection
- Impact Analysis of Speech Representation Learning Models for Acoustic Side-Channel Attack
- Graph Attention Design Choices Matter: A Controlled Study of LoRA-Adapted Audio Anti-Spoofing
- Speech Generation Speaker Poisoning: Capability Erasure in Zero-Shot Text-to-Speech
- Cloned Voices, Real Consequences: Evaluating Bias in Political Deepfake Detection for Electoral Integrity in Brazil
- CRAF: Cross-View Residual-Aware Fusion for Deepfake Speech Detection
- From Scores to Evidence: Auditable Decisions Can Improve Speech Deepfake Detection
- Spectral Masking and Interpolation Attack (SMIA): A Black-box Adversarial Attack against Voice Authentication and Anti-Spoofing Systems
- A Survey of Threats Against Voice Authentication and Anti-Spoofing Systems
- Domain-Incremental Learning for Multi-Channel Replay Speech Detection
- Not All Attacks Are Learned Equally in Speech Deepfake Detection
- Zero-Shot Temporal Localisation of Audio Deepfakes in Multi-Speaker Conversations