论文解读
别等整句说完：把数字人的手势变成一条受因果约束的数据流
音视频交互 | 6.9/10
论文速递
论文解读
把“该不该开口”拆成可追责时间表：TurnBench 逼出的轮次交接难题
语音交互 | 8.5/10
论文解读
语音助手的记忆为什么要分脑：VoiceMem 用 134 ms 换来 top-5 的长期理解
语音交互 | 6.6/10
论文解读
别再把同步分数当裁判：先问它量的是偏移、内容，还是感知代理
音视频理解 | 8.8/10
论文解读
一条咳嗽模型的跨国体检：高分为何更像设备在说话
音频分类 | 8.8/10
论文解读
让同一组录音按用户视角重新分组：AudioLens 如何把语音聚类变成集合推理
把“按什么视角聚类”交给自然语言指令，并让音频语言模型直接输出完整分区。
每日研究速递
语音/音乐/音频论文速递 2026-08-27
共分析 21 篇语音/AI 论文
论文解读
Anatomy of a Scam Call: What 10,000 real scam and spam calls reveal about how phone scammers operate
语音交互 | 7.3/10
论文解读
Arbitrary Polygon Oscillator: Generalizing Polygonal Synthesis to Arbitrary Shapes, Morphing, and Three-Dimensional Polyhedra
音乐生成 | 8.7/10
论文解读
Array-Agnostic Ambisonics Encoding via Diffusion Posterior Sampling
空间音频 | 7.5/10
论文解读
Benchmarking LLM Judges for Voice-Agent Evaluation: Reliability, Calibration, and Human Oversight
语音交互 | 6.6/10
论文解读
CoSTALA: Compositional Spatio-Temporal Audio-Language Alignment via Multi-Grain Hierarchical Contrastive Learning
空间音频 | 7.9/10
论文解读
Don't Just Listen, Try Planning: Graph-based Retrieval-Generation Agent for Long-form Audio Meeting Understanding
音频理解 | 7.8/10
论文解读
EM-KalmanNet: Learned Expectation-Maximization for Adaptive Tracking in Partially Known, Block-Wise Time-Varying State-Space Models
声源定位 | 8.8/10
论文解读
EmoTra-TTS: Smooth Intra-Utterance Emotion Transitions for Speech Synthesis
语音合成 | 9.6/10
论文解读
EXAM²: Extending Audio Understanding in Multilingual and Multimodal Analysis
音频理解 | 8.7/10
论文解读
FireRedAudio: A General-Purpose Audio Language Model with Decoupled Continuous Representations for Understanding and Generation
音频理解 | 8.7/10
论文解读
From local kernels to global form: modeling the emergence of musical content
音乐理解 | 8.2/10
论文解读
Investigating voiced and unvoiced regions of speech for audio deepfake detection
语音伪造检测 | 6.4/10
论文解读
LAION-BVD: A 10-Million-Hour Open Video Dataset for Multimodal Pre-training
音视频理解 | 9.4/10