论文解读
SPEAR: A Unified SSL Framework for Learning Speech and Audio Representations
音频理解 | 8.4/10
Posts
论文解读
Speech-Audio Compositional Attacks on Multimodal LLMs and Their Defense with SALMONN-Guard
音频理解 | 8.3/10
论文解读
Spherical Procrustes Alignment for Reliable Medical Audio Diagnosis
音频分类 | 8.2/10
论文解读
Stable Spectral Copula Alignment for Robust Multimodal Learning
鲁棒性 | 5.2/10
论文解读
STAR-VAE: Structured Topology-Aware Regularization for Audio Reconstruction and Generation
音频生成 | 7.9/10
论文解读
STARCaster: Spatio-Temporal AutoRegressive Video Diffusion for Identity- and View-Aware Talking Portraits
音视频生成 | 6.8/10
论文解读
Stream RAG: Instant and Accurate Spoken Dialogue Systems with Streaming Tool Usage
流式处理 | 7.2/10
论文解读
SURF: Separation via Unsupervised Remixing Flow
语音分离 | 6.2/10
论文解读
T2AV-Compass: Towards Unified Evaluation for Text-to-Audio-Video Generation
音视频生成 | 7.9/10
论文解读
TextME: Bridging Unseen Modalities Through Text Descriptions
TextME: Bridging Unseen Modalities Through Text Descriptions
论文解读
The Silent Thought: Modeling Internal Cognition in Full-Duplex Spoken Dialogue Models via Latent Reasoning
知识蒸馏 | 7/10
论文解读
TimeChat-Captioner: Scripting Multi-Scene Videos with Time-Aware and Structural Audio-Visual Captions
音视频理解 | 9.4/10
论文解读
TMD-Bench: A Multi-Level Evaluation Paradigm for Music–Dance Co-Generation
音视频生成 | 7.7/10
论文解读
Towards Streaming Synchronized Spatial Audio Generation via Autoregressive Diffusion Transformer
音视频生成 | 6.6/10
论文解读
Towards Understanding Modality Interaction in Multimodal Language Models via Partial Information Decomposition
音视频理解 | 5.3/10
论文解读
Two-dimensional quantization for geometry-aware audio coding
语音编码 | 7.6/10
论文解读
UltraLIF: Fully Differentiable Spiking Neural Networks via Ultradiscretization and Max-Plus Algebra
音频分类 | 6.7/10
论文解读
UniFLoW: Universal Multi-Modal Federated LoRA Fine-Tuning Framework with Analytical Aggregation
音视频问答 | 4.4/10
论文解读
Universal Algorithm-Implicit Learning
音频分类 | 6.5/10
论文解读
Unlocking Cross-Modal Biosignal Synthesis: A Temporally-Aware VAE-Diffusion Model
Unlocking Cross-Modal Biosignal Synthesis: A Temporally-Aware VAE-Diffusion Model