论文解读
Escaping the Procrustean Bed: Groupwise Orthogonal Connectors for Audio-Language Models
语音属性识别 | 7.8/10
鲁棒性
子标签
下方只统计已核验方向的论文记录，按已核身份去重，身份待核时按页面保留。“直接”只含明确标注该方向的论文；“含子树”同时包含下级方向。点击名称进入论文库继续筛选；数量与上方按标签名称收录的页面数不同。
- 对抗鲁棒性 直接 58 篇 · 含子树 58 篇
论文解读
An Intervention-Based Framework for Shortcut Diagnosis in Spoofing Countermeasures
语音伪造检测 | 6.1/10
论文解读
\(C^3\)ASD: Multi-Level Consistency-Driven Representation Learning
音视频理解 | 7.5/10
论文解读
Physiological Noise Augmentation Improves Non-Invasive Brain-to-Speech
语音识别 | 6/10
论文解读
UniSkip-Mamba: A Frequency-Aware State Space Model for Audio-Visual Temporal Forgery Localization
音视频理解 | 4.8/10
论文解读
Hidden in Plain Tokens: Simply Robust, Gradient-Free Watermark for Synthetic Audio
音频水印 | 7/10
论文解读
Joint Enhancement and Classification using Coupled Diffusion Models of Signals and Logits
语音识别 | 9.3/10
论文解读
Multimodal Fusion via Self-Consistent Task-Gradient Fields
鲁棒性 | 5.5/10
论文解读
SONAR: Spectral‑Contrastive Audio Residuals for Generalizable Deepfake Detection
语音伪造检测 | 7.8/10
论文解读
Stable Spectral Copula Alignment for Robust Multimodal Learning
鲁棒性 | 5.2/10
论文解读
Speaker head orientation estimation with a single microphone array using phase spectrogram features
声源定位 | 5.8/10
论文解读
Attacking UTMOS: Probing the Robustness of a Speech Quality Assessment Model
语音质量评估 | 8.6/10
论文解读
Two kinds of robustness are not the same: disentangling fault tolerance and low-SNR robustness in multi-domain event detection on real data
音频事件检测 | 8.9/10
论文解读
VeRe-Flow: Guiding Flow Matching toward Clean Speech via Velocity Contrastive Regularization and Representation Alignment for Noise-Robust Bandwidth Expansion
语音增强 | 7.7/10
论文解读
Supervised Post-training of Speech Foundation Models for Robust Adaptation in Speech Deepfake Detection
语音伪造检测 | 7.6/10
论文解读
An Analysis of Untrained Deep Reservoir Networks for Audio Surveillance
音频事件检测 | 8.8/10
论文解读
CORTIS: Text-Only Adaptation of Spoken Language Models for Task-Oriented Voice Agents
语音识别 | 7.7/10
论文解读
DASH: Dual-View Self-Distillation with Multi-Layer Hidden Representations for Robust Speech Recognition
语音识别 | 6.6/10
论文解读
NeuralMUSIC: A Hybrid Neural-Subspace Framework for Robot Sound Source Localization
声源定位 | 7.8/10
论文解读
Who Wins the Conflict? Mechanistic Interpretability of Text Bias in Audio LLMs
多模态模型 | 8.8/10