论文解读

Fast Multichannel NMF with Block-Diagonal Spatial Covariance Matrices for Efficient Blind Source Separation Using Distributed Microphone Arrays

语音分离 | 6.5/10

 · 更新于 2026-09-10 · 约 14 分钟 · 6659 字 阅读 →
论文解读

FormalASR: End-to-End Spoken Chinese to Formal Text

语音识别 | 6/10

 · 更新于 2026-09-10 · 约 15 分钟 · 7432 字 阅读 →
论文解读

GroupAffect-4: A Multimodal Dataset of Four-Person Collaborative Interaction

数据集 | 6.8/10

 · 更新于 2026-09-10 · 约 19 分钟 · 9307 字 阅读 →
论文解读

Heterogeneity-Aware Dataset Scheduling for Efficient Audio Large Language Model Training

音频问答 | 7/10

 · 更新于 2026-09-10 · 约 17 分钟 · 8063 字 阅读 →
论文解读

Mega-ASR: Towards In-the-wild^2 Speech Recognition via Scaling up Real-world Acoustic Simulation

语音识别 | 6.8/10

 · 更新于 2026-09-10 · 约 22 分钟 · 10575 字 阅读 →
论文解读

MSAVBench: Towards Comprehensive and Reliable Evaluation of Multi-Shot Audio-Video Generation

基准测试 | 6.5/10

 · 更新于 2026-09-10 · 约 17 分钟 · 8197 字 阅读 →
论文解读

OmniPro: A Comprehensive Benchmark for Omni-Proactive Streaming Video Understanding

视频理解 | 7.3/10

 · 更新于 2026-09-10 · 约 18 分钟 · 9001 字 阅读 →
论文解读

Optimising Neural Speech Codecs for 300bps Communication using Reinforcement Learning

音频编码 | 7/10

 · 更新于 2026-09-10 · 约 20 分钟 · 9569 字 阅读 →
论文解读

Precise and Simple Audio-to-Score Alignment

音乐信息检索 | 6.2/10

 · 更新于 2026-09-10 · 约 14 分钟 · 6923 字 阅读 →
论文解读

Sparse Fluid Antenna Arrays: Continuous Position Design Beyond Classical DOF Limits

声源定位 | 7/10

 · 更新于 2026-09-10 · 约 16 分钟 · 7558 字 阅读 →
论文解读

Towards Trust Calibration in Socially Interactive Agents: Investigating Gendered Multimodal Behaviors Generation with LLMs

社交智能体 | 5.9/10

 · 更新于 2026-09-10 · 约 21 分钟 · 10069 字 阅读 →
论文解读

When Vision Speaks for Sound

音视频 | 7.7/10

 · 更新于 2026-09-10 · 约 19 分钟 · 9514 字 阅读 →
每日研究速递

语音/音乐/音频论文速递 2026-05-20

共分析 20 篇语音/AI 论文

 · 更新于 2026-09-10 · 约 82 分钟 · 40963 字 阅读 →
论文解读

A Distribution Matching Approach to Neural Piano Transcription with Optimal Transport

音乐转录 | 5.5/10

 · 更新于 2026-09-10 · 约 16 分钟 · 7911 字 阅读 →
论文解读

A Fast Robust Adaptive filter using Improved Data-Reuse Method

声学回声消除 | 6.2/10

 · 更新于 2026-09-10 · 约 17 分钟 · 8222 字 阅读 →
论文解读

A Survey of Advancing Audio Super-Resolution and Bandwidth Extension from Discriminative to Generative Models

音频修复 | 8.1/10

 · 更新于 2026-09-10 · 约 17 分钟 · 8138 字 阅读 →
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

 · 更新于 2026-09-10 · 约 19 分钟 · 9033 字 阅读 →
论文解读

Analyzing Error Propagation in Korean Spoken QA with ASR-LLM Cascades

语音问答 | 5.6/10

 · 更新于 2026-09-10 · 约 17 分钟 · 8456 字 阅读 →
论文解读

Audio-Image Cross-Modal Retrieval with Onomatopoeic Images

音频检索 | 7/10

 · 更新于 2026-09-10 · 约 14 分钟 · 6984 字 阅读 →
论文解读

Beyond Transcripts: Iterative Peer-Editing with Audio Unlocks High-Quality Human Summaries of Conversational Speech

语音摘要 | 7.2/10

 · 更新于 2026-09-10 · 约 23 分钟 · 11227 字 阅读 →