论文解读
Few-Shot Open-Set Audio Classification Using Attention Information-Fused Prototypes
音频分类 | 6.8/10
音频分类
论文解读
BEST-RQ-2: Contextualize-Then-Predict, a Two-Step Approach for Self-Supervised Audio Representations
语音识别 | 6.9/10
论文解读
ZEBRA: Zero-Shot Entropy-Regularized Prompt Learning for Base-to-Novel Generalization in Audio-Language Models
音频分类 | 7.1/10
论文解读
WQ-Fusion: Dynamic Gated Attention for Cross-Domain Audio Representation
音频分类 | 6.7/10
论文解读
FoleySet: A Multi-Level Human-Annotated Foley Sound Dataset
音频分类 | 7/10
论文解读
A Multi-Stage Separation-and-Classification Framework Guided by Complementary Acoustic-to-Semantic Clues
音频分类 | 7.5/10
论文解读
Descriptor: Certus Caliber Classification Gunshot Dataset (C3GD)
音频分类 | 5.9/10
论文解读
Transductive Zero-Shot Audio Classification with Audio-Language Models
音频分类 | 6.4/10
论文解读
Turning music identification into a neural forward pass
音频分类 | 7.4/10
论文解读
Acoustic Prompting via Stage-wise Modulation for Few-Shot Learning in Audio Language Models
音频分类 | 8.3/10
论文解读
MambAdapter: Lightweight Mamba-Based Adapters for Parameter-Efficient Transfer Learning in Speech and Audio
语音识别 | 8.9/10
论文解读
Decoding Insect Song: A Multitask Semisupervised Orthoptera Bioacoustic Classifier
音频分类 | 8.7/10
论文解读
Dolph2Vec: Self-Supervised Representations of Dolphin Vocalizations
音频分类 | 7.2/10
论文解读
Few-shot Class-variable Incremental Audio Classification via Prototype Adaptation and Pseudo Class-variable Training
音频分类 | 6.9/10
论文解读
Sound Effects Dataset Unification With the Universal Category System
音频分类 | 6.9/10
论文解读
Drift-Augmented Scoring: Text-Derived Noise Robustness for Zero-Shot Audio-Language Classification
音频分类 | 10/10
论文解读
C2GA: A Class-Controllable Generative Augmentation Framework for Respiratory Sound Classification
音频分类 | 7.3/10
论文解读
Parameter-efficient Dual-encoder Architecture with Differentiable Choquet Integral Fusion for Underwater Acoustic Classification
音频分类 | 6.4/10
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
ChildVox: A Speech, Audio, and Large Audio-Language Model Benchmark in Understanding and Characterizing Sound across Childhood
语音识别 | 8/10