论文解读
SpongeBob: Sync-Aware Harmonious Audio-Visual Generative Editing
语音编辑 | 8.6/10
多模态模型
论文解读
Thaka at KSAA-2026 Task 2: Regularized Fine-Tuning for Arabic Speech Diacritization
语音增强 | 5.5/10
论文解读
Toward Native Multimodal Modeling: A Roadmap
多模态模型 | 10/10
论文解读
Zero-Shot Parkinson's Disease Detection from Speech: Comparing Large Audio and Language Models
大语言模型 | 5/10
每日研究速递
语音/音乐/音频论文速递 2026-05-26
共分析 27 篇语音/AI 论文
论文解读
EvalVerse: Pipeline-Aware and Expert-Calibrated Benchmarking for Professional Cinematic Video Generation
音视频 | 7.1/10
论文解读
Frame-Aligned Fusion of Canary and WavLM for Non-Intrusive Intelligibility Prediction of Hearing-Aid-Processed Speech
语音质量评估 | 10/10
每日研究速递
语音/音乐/音频论文速递 2026-05-25
共分析 19 篇语音/AI 论文
论文解读
A Survey of Audio Reasoning in Multimodal Foundation Models
音频推理 | 7.7/10
论文解读
CRAFT: Critic-Refined Adaptive Key-Frame Targeting for Multimodal Video Question Answering
多模态问答 | 6.6/10
论文解读
DuplexSLA: A Full-Duplex Spoken Language Model with Synchronized Speech, Language, and Action
语音对话系统 | 7.8/10
论文解读
MSAVBench: Towards Comprehensive and Reliable Evaluation of Multi-Shot Audio-Video Generation
基准测试 | 8.1/10
论文解读
Stage-adaptive Token Selection for Efficient Omni-modal LLMs
多模态模型 | 7.7/10
论文解读
CounterFlow: A Two-Phase Inference-Time Sampling for Counterfactual Video Foley Generation
音频生成 | 6/10
论文解读
EMO-BOOST: Emotion-Augmented Audio-Visual Features for Improved Generalization in Deepfake Detection
音频深度伪造检测 | 7.2/10
论文解读
GroupAffect-4: A Multimodal Dataset of Four-Person Collaborative Interaction
数据集 | 6.8/10
论文解读
MSAVBench: Towards Comprehensive and Reliable Evaluation of Multi-Shot Audio-Video Generation
基准测试 | 6.5/10
论文解读
OmniPro: A Comprehensive Benchmark for Omni-Proactive Streaming Video Understanding
视频理解 | 7.3/10
论文解读
When Vision Speaks for Sound
音视频 | 7.7/10
论文解读
Acoustic Interference: A New Paradigm Weaponizing Acoustic Latent Semantic for Universal Jailbreak against Large Audio Language Models
音频安全 | 8.7/10