每日研究速递
语音/音乐/音频论文速递 2026-05-06
共分析 23 篇语音/AI 论文
多任务学习
论文解读
Multi-Axis Speech Similarity via Factor-Partitioned Embeddings
音频检索 | 6.0/10
论文解读
A Hidden Semantic Bottleneck in Conditional Embeddings of Diffusion Transformers
图像生成 | 8.5/10
论文解读
Bridging Piano Transcription and Rendering via Disentangled Score Content and Style
音乐信息检索 | 8.0/10
论文解读
From Natural Alignment to Conditional Controllability in Multimodal Dialogue
语音合成 | 8.0/10
论文解读
Group Cognition Learning: Making Everything Better Through Governed Two-Stage Agents Collaboration
多模态模型 | 7.5/10
论文解读
MMAudio-LABEL: Audio Event Labeling via Audio Generation for Silent Video
音频生成 | 7.5/10
论文解读
OptMerge: Unifying Multimodal LLM Capabilities and Modalities via Model Merging
模型比较 | 7.0/10
论文解读
OWL : Geometry-Aware Spatial Reasoning for Audio Large Language Models
空间音频 | 8.0/10
论文解读
SpeechOp: Inference-Time Task Composition for Generative Speech Processing
语音增强 | 7.5/10
论文解读
WAVE: Learning Unified & Versatile Audio-Visual Embeddings with Multimodal LLM
音频检索 | 8.0/10
每日研究速递
语音/音乐/音频论文速递 2026-05-04
共分析 14 篇语音/AI 论文
论文解读
Bridging Piano Transcription and Rendering via Disentangled Score Content and Style
音乐信息检索 | 8.0/10
论文解读
Human Behavior Atlas: Benchmarking Unified Psychological And Social Behavior Understanding
多模态模型 | 7.5/10
论文解读
Speech World Model: Causal State–Action Planning with Explicit Reasoning for Speech
语音情感识别 语音对话系统 | 9.0/10
论文解读
SpeechOp: Inference-Time Task Composition for Generative Speech Processing
语音增强 | 7.5/10
论文解读
WAVE: Learning Unified & Versatile Audio-Visual Embeddings with Multimodal LLM
音频检索 视频检索 | 8.5/10
论文解读
EmoTransCap: Dataset and Pipeline for Emotion Transition-Aware Speech Captioning in Discourses
语音情感识别 | 7.5/10
论文解读
A Task-Aware Dual-Level Self-Supervised Learning Method for Effective Sound Event Detection
音频事件检测 | 7.5/10
论文解读
ACAVCaps: Enabling Large-Scale Training for Fine-Grained and Diverse Audio Understanding
音频分类 | 8.5/10