论文解读
MOSAIC: Interpretable Multi-Token Cross-Attention of Biophonetic and Self-Supervised Representations for Unified Voice Anti-Spoofing
语音伪造检测 | 6.3/10
领域适应
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。
- 测试时自适应 直接 93 篇 · 含子树 93 篇
论文解读
QuaSR: Quality-Aware Sample Reweighting for Pacific Indigenous Speech Recognition
语音识别 | 6/10
论文解读
SynSFX: Multi-Model Sound Effects Synthesis Dataset for Deepfake Detection and Evaluation
音频伪造检测 | 6.5/10
论文解读
Training-Free Model Selection and Domain-Aware Score Calibration for First-Shot Anomalous Sound Detection
音频事件检测 | 7.3/10
论文解读
MetaPerch: Learning from metadata for bioacoustics foundation models
音频分类 | 6.5/10
论文解读
Gumbel-BEARD: Automatic Layer Selection for Self-Supervised Adaptation of Whisper in Low-Resource Domains
语音识别 | 9.1/10
论文解读
CoughSense: Five-Class Respiratory Disease Classification via Whisper Encoder Fine-Tuning and Dual-Encoder Cross-Attention Fusion with Balanced Contrastive Learning
数据增强 | 9.1/10
论文解读
Context-aware child-directed speech detection from long-form recordings
自监督学习 | 8.5/10
论文解读
几何主导下如何减出材料：GaMi 的跨模态相减式解耦
针对几何变化压制材料特征的问题，GaMi 用共位毫米波与声学的共享几何一致性做对齐-校准-相减解耦，并以样本间对比抑制残差，在 20 类材料上以 95.2% 的总体准确率显著优于单模态基线，代价是需双模态同步采集与多目标联合训练。
论文解读
Cost-Effective Model Evaluation with Meta-Learning
迁移学习 | 5.4/10
论文解读
A strongly annotated passive acoustic dataset for tropical bird monitoring
生物声学 | 7.2/10
论文解读
CoarseSoundNet: Building a reliable model for ecological soundscape analysis
音频分类 | 8.5/10
论文解读
Ordering Matters: Rank-Aware Selective Fusion for Blended Emotion Recognition
多模态情感识别 | 5.0/10
论文解读
DASM: Domain-Aware Sharpness Minimization for Multi-Domain Voice Stream Steganalysis
语音伪造检测 | 7/10
论文解读
PAREDA: A Multi-Accent Speech Dataset of Natural Language Processing Research Discussions
语音数据集 | 6.5/10
论文解读
Refining Pseudo-Audio Prompts with Speech-Text Alignment for Text-Only Domain Adaptation in LLM-Based ASR
语音识别 | 7.5/10
论文解读
Rethinking Entropy Minimization in Test-Time Adaptation for Autoregressive Models
语音识别 | 6.0/10
论文解读
Empirical Study of Pop and Jazz Mix Ratios for Genre-Adaptive Chord Generation
音乐生成 | 7.5/10
论文解读
OceanPile: A Large-Scale Multimodal Ocean Corpus for Foundation Models
音频分类 | 7.5/10
论文解读
DECKER: Domain-invariant Embedding for Cross-Keyboard Extraction and Recognition
音频安全 | 7.5/10