音频生成论文趋势 2023–2026

音乐与音效生成

统计范围：NeurIPS、ICLR、ICML、CVPR 四个会议，2023–2026 年，共 357 篇被归入该主题的论文。

主要结论

每年论文数

各会议论文数

按年份和会议统计

音频生成论文数，按年份和会议
年份NeurIPSICLRICMLCVPR合计
20238611732
20241822161773
202532431031116
202621642526136

代表论文

按年份和会议均匀挑选，方便快速看到每一届的样貌

全部音频生成论文

年份全部2023202420252026
会议全部NeurIPSICLRICMLCVPR

共 357 篇，第 3 / 8 页

  1. ICML 2026MusicDET: Zero-Shot AI-Generated Music Detection
  2. ICML 2026PHALAR: Phasors for Learned Musical Audio Representations
  3. ICML 2026PhaseCoder: Microphone Geometry-Agnostic Spatial Audio Understanding for Multimodal LLMs
  4. ICML 2026Polyphonia: Zero-Shot Timbre Transfer in Polyphonic Music with Acoustic-Informed Attention Calibration
  5. ICML 2026SAM Audio: Segment Anything in Audio
  6. ICML 2026Scaling Transformers for End-to-End Discrete Audio Tokenization
  7. ICML 2026SONAR: Spectral‑Contrastive Audio Residuals for Generalizable Deepfake Detection
  8. ICML 2026SonicMaster: Towards Controllable All-in-One Music Restoration and Mastering
  9. ICML 2026SPEAR: A Unified SSL Framework for Learning Speech and Audio Representations
  10. ICML 2026Spherical Procrustes Alignment for Reliable Medical Audio Diagnosis
  11. ICML 2026STAR-VAE: Structured Topology-Aware Regularization for Audio Reconstruction and Generation
  12. ICML 2026T2AV-Compass: Towards Unified Evaluation for Text-to-Audio-Video Generation
  13. ICML 2026TMD-Bench: A Multi-Level Evaluation Paradigm for Music–Dance Co-Generation
  14. ICML 2026Towards Streaming Synchronized Spatial Audio Generation via Autoregressive Diffusion Transformer
  15. ICML 2026Two-dimensional quantization for geometry-aware audio coding
  16. NeurIPS 2026A Unified Audio Language Model with Text-Aligned Factorized Audio Tokenization
  17. NeurIPS 2026ANCHOR: Audio-Visually Grounded Chain-of-Thought Reasoning Benchmark
  18. NeurIPS 2026Asymmetric Phase Coding Audio Watermarking
  19. NeurIPS 2026Audible World Models: Spatially Aware Sound Generation for 3D Worlds
  20. NeurIPS 2026AudioCALM: Continuous Autoregressive Language Modeling for Universal Audio Generation
  21. NeurIPS 2026Continuous Audio Thinking for Large Audio Language Models
  22. NeurIPS 2026FlexCover: Flexible Cover Song Generation via Symbolic Lead Sheet Control
  23. NeurIPS 2026Generating the Unheard: Phylogeny-Guided Latent Generation for Ancestral Sound Reconstruction
  24. NeurIPS 2026MAEB: Massive Audio Embedding Benchmark
  25. NeurIPS 2026MFlowAudio: Efficient Text-to-Audio Synthesis via Mamba-based Stateful Flow Matching
  26. NeurIPS 2026Native Audio-Visual Alignment for Generation
  27. NeurIPS 2026PitchBench: Measuring Pitch Hearing in Audio-Language Models
  28. NeurIPS 2026RAIL: Rethinking Auditory Intelligence in Large Audio-Language Models with a CHC-Grounded Benchmark
  29. NeurIPS 2026Rubato: Transcribing Piano Music with Timestamps
  30. NeurIPS 2026RVCBench: Benchmarking Robustness of Voice Cloning Across Modern Audio Generation Models
  31. NeurIPS 2026SceneShifter: Training-free Multi-Scene Temporal Control for Audio-driven Human Animation
  32. NeurIPS 2026She Performs Your Voice: A Unified Speech and Dance Motion Model
  33. NeurIPS 2026StableAvatar: Ultra-Long Audio-Driven Avatar Video Generation
  34. NeurIPS 2026V2M-Zero: Zero-Pair Time-Aligned Video-to-Music Generation
  35. NeurIPS 2026VocalCoachBench: Benchmarking Audio-Language Models on Expert Feedback for Singing
  36. NeurIPS 2026WaveGen: Truly End-to-End Waveform Generation via Internal Spectral Trajectory Learning
  37. CVPR 2025Animate and Sound an Image
  38. CVPR 2025AudCast: Audio-Driven Human Video Generation by Cascaded Diffusion Transformers
  39. CVPR 2025Co-Speech Gesture Video Generation with Implicit Motion-Audio Entanglement
  40. CVPR 2025Customized Condition Controllable Generation for Video Soundtrack
  41. CVPR 2025DistinctAD: Distinctive Audio Description Generation in Contexts
  42. CVPR 2025EmotiveTalk: Expressive Talking Head Generation through Audio Information Decoupling and Emotional Video Diffusion
  43. CVPR 2025Enhancing Dance-to-Music Generation via Negative Conditioning Latent Diffusion Model
  44. CVPR 2025Exploring Timeline Control for Facial Motion Generation
  45. CVPR 2025FilmComposer: LLM-Driven Music Production for Silent Film Clips
  46. CVPR 2025Foley-Flow: Coordinated Video-to-Audio Generation with Masked Audio-Visual Alignment and Dynamic Conditional Flows
  47. CVPR 2025Hearing Hands: Generating Sounds from Physical Interactions in 3D Scenes
  48. CVPR 2025Improving Sound Source Localization with Joint Slot Attention on Image and Audio
  49. CVPR 2025INFP: Audio-Driven Interactive Head Generation in Dyadic Conversations
  50. CVPR 2025KeyFace: Expressive Audio-Driven Facial Animation for Long Sequences via KeyFrame Interpolation

在 Claude、Cursor 里直接问这个趋势

接上 Paperlist MCP 后，写综述、挑方向或准备投稿时，不用离开对话框就能拿到这页的数字：每年各会议的论文数、增长倍数、涨得最快的子方向和代表论文，AI 会按你的问题整理。

可以直接复制这句话问 AI

用 paperlist 查音频生成在 ICLR 2023–2026 的论文趋势，哪一年涨得最快？

AI 会调用的工具：get_topic_stats {"topic": "audio-generation"}

两分钟接入 Paperlist MCP（Claude Code、Cursor、Codex、ChatGPT）

常见问题

2023–2026 年四大会议一共有多少篇音频生成论文？
共 357 篇，按年份分别是 2023 年 32 篇、2024 年 73 篇、2025 年 116 篇、2026 年 136 篇。
NeurIPS 2026 有多少篇音频生成论文？
NeurIPS 2026 有 21 篇音频生成论文，上一届是 32 篇。
ICLR 2026 有多少篇音频生成论文？
ICLR 2026 有 64 篇音频生成论文，上一届是 43 篇。
ICML 2026 有多少篇音频生成论文？
ICML 2026 有 25 篇音频生成论文，上一届是 10 篇。
CVPR 2026 有多少篇音频生成论文？
CVPR 2026 有 26 篇音频生成论文，上一届是 31 篇。
哪个会议的音频生成论文最多？
ICLR，2023–2026 年共 135 篇。

「语音与音频」下的其他主题