论文解读
Break-the-Beat! Controllable MIDI-to-Drum Audio Synthesis
音频生成 | 6.8/10
音频生成
子标签
下方只统计已核验方向的论文记录，按已核身份去重，身份待核时按页面保留。“直接”只含明确标注该方向的论文；“含子树”同时包含下级方向。点击名称进入论文库继续筛选；数量与上方按标签名称收录的页面数不同。
- 视频到声音生成 直接 62 篇 · 含子树 62 篇
论文解读
FSD50K-Solo: Automated Curation of Single-Source Sound Events
数据清洗 | 5.5/10
论文解读
Seconds-Aligned PCA-DAC Latent Diffusion for Symbolic-to-Audio Drum Rendering
音频生成 | 7.0/10
论文解读
AuDirector: A Self-Reflective Closed-Loop Framework for Immersive Audio Storytelling
音频生成 | 6.0/10
论文解读
ChladniSonify: A Visual-Acoustic Mapping Method for Chladni Patterns in New Media Art Creation
音频生成 | 6.0/10
论文解读
Remix the Timbre: Diffusion-Based Style Transfer Across Polyphonic Stems
音色迁移 | 5.5/10
论文解读
AVI-Edit: Audio-sync Video Instance Editing with Granularity-Aware Mask Refiner
视频编辑 | 8.0/10
论文解读
Stage-adaptive audio diffusion modeling
音频生成 | 7.0/10
论文解读
AC-Foley: Reference-Audio-Guided Video-to-Audio Synthesis with Acoustic Transfer
音频生成 | 8.0/10
论文解读
AudioX: A Unified Framework for Anything-to-Audio Generation
音频生成 | 7.5/10
论文解读
Aurelius: Relation Aware Text-to-Audio Generation At Scale
音频生成 | 8.0/10
论文解读
Fast Text-to-Audio Generation with One-Step Sampling via Energy-Scoring and Auxiliary Contextual Representation Distillation
音频生成 | 7.5/10
论文解读
Flow2GAN: Hybrid Flow Matching and GAN with Multi-Resolution Network for Few-step High-Fidelity Audio Generation
音频生成 | 8.0/10
论文解读
FlowBind: Efficient Any-to-Any Generation with Bidirectional Flows
跨模态生成 | 9.5/10
会议任务专题
ICLR 2026 - 音频生成
共 9 篇 ICLR 2026 音频生成 方向论文
论文解读
Latent Fourier Transform
音乐生成 | 8.5/10
论文解读
LayerSync: Self-aligning Intermediate Layers
音频生成 | 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
PrismAudio: Decomposed Chain-of-Thought and Multi-dimensional Rewards for Video-to-Audio Generation
音频生成 | 9.0/10
论文解读
SCRAPL: Scattering Transform with Random Paths for Machine Learning
音频生成 | 8.5/10