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 79 篇，第 1 / 2 页

  1. NeurIPS 2026A Unified Audio Language Model with Text-Aligned Factorized Audio Tokenization
  2. NeurIPS 2026ANCHOR: Audio-Visually Grounded Chain-of-Thought Reasoning Benchmark
  3. NeurIPS 2026Asymmetric Phase Coding Audio Watermarking
  4. NeurIPS 2026Audible World Models: Spatially Aware Sound Generation for 3D Worlds
  5. NeurIPS 2026AudioCALM: Continuous Autoregressive Language Modeling for Universal Audio Generation
  6. NeurIPS 2026Continuous Audio Thinking for Large Audio Language Models
  7. NeurIPS 2026FlexCover: Flexible Cover Song Generation via Symbolic Lead Sheet Control
  8. NeurIPS 2026Generating the Unheard: Phylogeny-Guided Latent Generation for Ancestral Sound Reconstruction
  9. NeurIPS 2026MAEB: Massive Audio Embedding Benchmark
  10. NeurIPS 2026MFlowAudio: Efficient Text-to-Audio Synthesis via Mamba-based Stateful Flow Matching
  11. NeurIPS 2026Native Audio-Visual Alignment for Generation
  12. NeurIPS 2026PitchBench: Measuring Pitch Hearing in Audio-Language Models
  13. NeurIPS 2026RAIL: Rethinking Auditory Intelligence in Large Audio-Language Models with a CHC-Grounded Benchmark
  14. NeurIPS 2026Rubato: Transcribing Piano Music with Timestamps
  15. NeurIPS 2026RVCBench: Benchmarking Robustness of Voice Cloning Across Modern Audio Generation Models
  16. NeurIPS 2026SceneShifter: Training-free Multi-Scene Temporal Control for Audio-driven Human Animation
  17. NeurIPS 2026She Performs Your Voice: A Unified Speech and Dance Motion Model
  18. NeurIPS 2026StableAvatar: Ultra-Long Audio-Driven Avatar Video Generation
  19. NeurIPS 2026V2M-Zero: Zero-Pair Time-Aligned Video-to-Music Generation
  20. NeurIPS 2026VocalCoachBench: Benchmarking Audio-Language Models on Expert Feedback for Singing
  21. NeurIPS 2026WaveGen: Truly End-to-End Waveform Generation via Internal Spectral Trajectory Learning
  22. NeurIPS 2025🎧MOSPA: Human Motion Generation Driven by Spatial Audio
  23. NeurIPS 2025AHa-Bench: Benchmarking Audio Hallucinations in Large Audio-Language Models
  24. NeurIPS 2025Audio Flamingo 3: Advancing Audio Intelligence with Fully Open Large Audio Language Models
  25. NeurIPS 2025Audio Super-Resolution with Latent Bridge Models
  26. NeurIPS 2025Audio-Sync Video Generation with Multi-Stream Temporal Control
  27. NeurIPS 2025AudSemThinker: Enhancing Audio-Language Models Through Reasoning over Semantics of Sound
  28. NeurIPS 2025BNMusic: Blending Environmental Noises into Personalized Music
  29. NeurIPS 2025BRACE: A Benchmark for Robust Audio Caption Quality Evaluation
  30. NeurIPS 2025DroneAudioset: An Audio Dataset for Drone-based Search and Rescue
  31. NeurIPS 2025Failure by Interference: Language Models Make Balanced Parentheses Errors When Faulty Mechanisms Overshadow Sound Ones
  32. NeurIPS 2025Improving Target Sound Extraction via Disentangled Codec Representations with Privileged Knowledge Distillation
  33. NeurIPS 2025JavisGPT: A Unified Multi-modal LLM for Sounding-Video Comprehension and Generation
  34. NeurIPS 2025Let Them Talk: Audio-Driven Multi-Person Conversational Video Generation
  35. NeurIPS 2025LeVo: High-Quality Song Generation with Multi-Preference Alignment
  36. NeurIPS 2025Massive Sound Embedding Benchmark (MSEB)
  37. NeurIPS 2025MEGADance: Mixture-of-Experts Architecture for Genre-Aware 3D Dance Generation
  38. NeurIPS 2025MGE-LDM: Joint Latent Diffusion for Simultaneous Music Generation and Source Extraction
  39. NeurIPS 2025MoCha: Towards Movie-Grade Talking Character Generation
  40. NeurIPS 2025Model-Guided Dual-Role Alignment for High-Fidelity Open-Domain Video-to-Audio Generation
  41. NeurIPS 2025MRSAudio: A Large-Scale Multimodal Recorded Spatial Audio Dataset with Refined Annotations
  42. NeurIPS 2025OmniTalker: One-shot Real-time Text-Driven Talking Audio-Video Generation With Multimodal Style Mimicking
  43. NeurIPS 2025Resounding Acoustic Fields with Reciprocity
  44. NeurIPS 2025Robust Distortion-Free Watermark for Autoregressive Audio Generation Models
  45. NeurIPS 2025SAO-Instruct: Free-form Audio Editing using Natural Language Instructions
  46. NeurIPS 2025SongBloom: Coherent Song Generation via Interleaved Autoregressive Sketching and Diffusion Refinement
  47. NeurIPS 2025Streaming Audio Generation from Discrete Tokens via Streaming Flow Matching
  48. NeurIPS 2025ThinkSound: Chain-of-Thought Reasoning in Multimodal LLMs for Audio Generation and Editing
  49. NeurIPS 2025Towards A Translative Model of Sperm Whale Vocalization
  50. NeurIPS 2025Unbiased Sliced Wasserstein Kernels for High-Quality Audio Captioning

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