论文解读
ClawMark: A Living-World Benchmark for Multi-Turn, Multi-Day, Multimodal Coworker Agents
基准测试 | 7.0/10
论文速递
论文解读
Cross-Linguistic Rhythmic and Spectral Feature-Based Analysis of Nyishi and Adi: Two Under-Resourced Languages of Arunachal Pradesh
Cross-Linguistic Rhythmic and Spectral Feature-Based Analysis of Nyishi and Adi: Two Under-Resourced Languages of Arunachal Pradesh
论文解读
Cutscene Agent: An LLM Agent Framework for Automated 3D Cutscene Generation
生成模型 | 8.5/10
论文解读
缺失与偏置并存时如何做鲁棒的多模态情感分析：门控序列修复与平衡跨模态注意的协同
📄 缺失与偏置并存时如何做鲁棒的多模态情感分析：门控序列修复与平衡跨模态注意的协同 会议论文 ID：conference:icassp:2026:icassp-arnumber:11460389
论文解读
Generative UI as an Accessibility Bridge: Lessons from C2C E-Commerce
无障碍 | 6.5/10
论文解读
Huí Sù: Co-constructing a Dual Feedback Apparatus
音乐生成 | 5.5/10
论文解读
Human-1 by Josh Talks: A Full-Duplex Conversational Modeling Framework in Hindi using Real-World Conversations
语音对话系统 | 7.5/10
论文解读
Independent-Component-Based Encoding Models of Brain Activity During Story Comprehension
神经编码 | 7.5/10
论文解读
保留高维 XLS-R 特征时单层 KAN 能否以更少参数替代复杂后端
📄 保留高维 XLS-R 特征时单层 KAN 能否以更少参数替代复杂后端 会议论文 ID：conference:icassp:2026:icassp-arnumber:11460320
论文解读
Korean aegyo speech shows systematic F1 increase to signal childlike qualities
语音情感识别 | 6.0/10
论文解读
Mitigating Shared-Private Branch Imbalance via Dual-Branch Rebalancing for Multimodal Sentiment Analysis
多模态模型 | 7.5/10
论文解读
用带噪混合当高噪声步监督：Mix2Morph 如何把加法叠加训练成可控的声音注入
📄 用带噪混合当高噪声步监督：Mix2Morph 如何把加法叠加训练成可控的声音注入 会议论文 ID：conference:icassp:2026:icassp-arnumber:11460386
论文解读
ML-SAN: Multi-Level Speaker-Adaptive Network for Emotion Recognition in Conversations
语音情感识别 | 8.0/10
论文解读
MMEB-V3: Measuring the Performance Gaps of Omni-Modality Embedding Models
基准测试 | 7.5/10
论文解读
Monitoring exposure-length variations in submarine power cables using distributed fiber-optic sensing
音频事件检测 | 6.5/10
论文解读
Mutual Forcing: Dual-Mode Self-Evolution for Fast Autoregressive Audio-Video Character Generation
音频生成 | 7.5/10
论文解读
Nemotron 3 Nano Omni: Efficient and Open Multimodal Intelligence
多模态模型 | 8.5/10
论文解读
Praxy Voice: Voice-Prompt Recovery + BUPS for Commercial-Class Indic TTS from a Frozen Non-Indic Base at Zero Commercial-Training-Data Cost
语音合成 | 8.0/10
论文解读
PSP: An Interpretable Per-Dimension Accent Benchmark for Indic Text-to-Speech
基准测试 | 7.5/10
论文解读
RAS: a Reliability Oriented Metric for Automatic Speech Recognition
语音识别 | 7.5/10