论文解读
Addressing Gradient Misalignment in Data-Augmented Training for Robust Speech Deepfake Detection
语音伪造检测 | 7.0/10
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
Advanced modeling of interlanguage speech intelligibility benefit with L1-L2 multi-task learning using differentiable K-means for accent-robust discrete token-based ASR
语音识别 | 7.0/10
论文解读
Adversarial Defense via Generative Speech Enhancement Module
语音增强 对抗防御 | 7.5/10
论文解读
Adversarial Fine-Tuning on Speech Foundation Model with Vulnerable Attention Consistency Regularization for Robust Speech Recognition
语音识别 | 7.5/10
论文解读
AFT: An Exemplar-Free Class Incremental Learning Method for Environmental Sound Classification
音频分类 | 7.0/10
论文解读
AI-Generated Music Detection in Broadcast Monitoring
音频深度伪造检测 | 7.0/10
论文解读
AMBER2: Dual Ambiguity-Aware Emotion Recognition Applied to Speech and Text
语音情感识别 | 8.0/10
论文解读
AmbiDrop: Array-Agnostic Speech Enhancement Using Ambisonics Encoding and Dropout-Based Learning
语音增强 | 7.0/10
论文解读
AnyAccomp: Generalizable Accompaniment Generation Via Quantized Melodic Bottleneck
音乐生成 | 8.0/10
论文解读
AnyRIR: Robust Non-Intrusive Room Impulse Response Estimation in the Wild
空间音频 | 7.0/10
论文解读
AQUA-Bench: Beyond finding answers to knowing when there are None in Audio Question Answering
音频问答 | 7.0/10
论文解读
Are Modern Speech Enhancement Systems Vulnerable to Adversarial Attacks?
语音增强 | 7.5/10
论文解读
Audio Classification Models are Vulnerable to Filter Perturbations
音频分类 | 7.5/10
论文解读
Audio Deepfake Detection at the First Greeting: "Hi!"
音频深度伪造检测 | 7.5/10
论文解读
AudioFuse: Unified Spectral-Temporal Learning Via A Hybrid VIT-1D CNN Architecture for Phonocardiogram Classification
音频分类 | 7.5/10
论文解读
AURA: A Stegaformer-Based Scalable Deep Audio Watermark with Extreme Robustness
音频水印 | 7.5/10
论文解读
Auxiliary Multi-Label Training For Improving the Robustness of Audio Deepfake Detection on AI-Processed Data
音频深度伪造检测 | 6.5/10
论文解读
AVATAR: Audio-Visual Adaptive Fusion via Trained Agent Reinforcement for Multimodal Deepfake Detection
音频深度伪造检测 | 7.5/10
论文解读
Bloodroot: When Watermarking Turns Poisonous for Stealthy Backdoor
音频安全 | 7.5/10
论文解读
Brainprint-Modulated Target Speaker Extraction
语音分离 | 8.0/10