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 5 / 8 页

  1. ICLR 2025TabDiff: a Mixed-type Diffusion Model for Tabular Data Generation
  2. ICLR 2025Talking Turns: Benchmarking Audio Foundation Models on Turn-Taking Dynamics
  3. ICLR 2025TANGO: Co-Speech Gesture Video Reenactment with Hierarchical Audio Motion Embedding and Diffusion Interpolation
  4. ICLR 2025The KoLMogorov Test: Compression by Code Generation
  5. ICLR 2025Training-free Camera Control for Video Generation
  6. ICLR 2025UniWav: Towards Unified Pre-training for Speech Representation Learning and Generation
  7. ICLR 2025ViSAGe: Video-to-Spatial Audio Generation
  8. ICLR 2025VLMaterial: Procedural Material Generation with Large Vision-Language Models
  9. ICLR 2025Weakly Supervised Video Scene Graph Generation via Natural Language Supervision
  10. ICLR 2025X-NeMo: Expressive Neural Motion Reenactment via Disentangled Latent Attention
  11. ICML 2025ALMTokenizer: A Low-bitrate and Semantic-rich Audio Codec Tokenizer for Audio Language Modeling
  12. ICML 2025Audio Flamingo 2: An Audio-Language Model with Long-Audio Understanding and Expert Reasoning Abilities
  13. ICML 2025CodeSync: Synchronizing Large Language Models with Dynamic Code Evolution at Scale
  14. ICML 2025Efficient Fine-Grained Guidance for Diffusion Model Based Symbolic Music Generation
  15. ICML 2025ETTA: Elucidating the Design Space of Text-to-Audio Models
  16. ICML 2025IMPACT: Iterative Mask-based Parallel Decoding for Text-to-Audio Generation with Diffusion Modeling
  17. ICML 2025MuseControlLite: Multifunctional Music Generation with Lightweight Conditioners
  18. ICML 2025OmniAudio: Generating Spatial Audio from 360-Degree Video
  19. ICML 2025Sounding that Object: Interactive Object-Aware Image to Audio Generation
  20. ICML 2025Supervised Contrastive Learning from Weakly-Labeled Audio Segments for Musical Version Matching
  21. NeurIPS 2025🎧MOSPA: Human Motion Generation Driven by Spatial Audio
  22. NeurIPS 2025AHa-Bench: Benchmarking Audio Hallucinations in Large Audio-Language Models
  23. NeurIPS 2025Audio Flamingo 3: Advancing Audio Intelligence with Fully Open Large Audio Language Models
  24. NeurIPS 2025Audio Super-Resolution with Latent Bridge Models
  25. NeurIPS 2025Audio-Sync Video Generation with Multi-Stream Temporal Control
  26. NeurIPS 2025AudSemThinker: Enhancing Audio-Language Models Through Reasoning over Semantics of Sound
  27. NeurIPS 2025BNMusic: Blending Environmental Noises into Personalized Music
  28. NeurIPS 2025BRACE: A Benchmark for Robust Audio Caption Quality Evaluation
  29. NeurIPS 2025DroneAudioset: An Audio Dataset for Drone-based Search and Rescue
  30. NeurIPS 2025Failure by Interference: Language Models Make Balanced Parentheses Errors When Faulty Mechanisms Overshadow Sound Ones
  31. NeurIPS 2025Improving Target Sound Extraction via Disentangled Codec Representations with Privileged Knowledge Distillation
  32. NeurIPS 2025JavisGPT: A Unified Multi-modal LLM for Sounding-Video Comprehension and Generation
  33. NeurIPS 2025Let Them Talk: Audio-Driven Multi-Person Conversational Video Generation
  34. NeurIPS 2025LeVo: High-Quality Song Generation with Multi-Preference Alignment
  35. NeurIPS 2025Massive Sound Embedding Benchmark (MSEB)
  36. NeurIPS 2025MEGADance: Mixture-of-Experts Architecture for Genre-Aware 3D Dance Generation
  37. NeurIPS 2025MGE-LDM: Joint Latent Diffusion for Simultaneous Music Generation and Source Extraction
  38. NeurIPS 2025MoCha: Towards Movie-Grade Talking Character Generation
  39. NeurIPS 2025Model-Guided Dual-Role Alignment for High-Fidelity Open-Domain Video-to-Audio Generation
  40. NeurIPS 2025MRSAudio: A Large-Scale Multimodal Recorded Spatial Audio Dataset with Refined Annotations
  41. NeurIPS 2025OmniTalker: One-shot Real-time Text-Driven Talking Audio-Video Generation With Multimodal Style Mimicking
  42. NeurIPS 2025Resounding Acoustic Fields with Reciprocity
  43. NeurIPS 2025Robust Distortion-Free Watermark for Autoregressive Audio Generation Models
  44. NeurIPS 2025SAO-Instruct: Free-form Audio Editing using Natural Language Instructions
  45. NeurIPS 2025SongBloom: Coherent Song Generation via Interleaved Autoregressive Sketching and Diffusion Refinement
  46. NeurIPS 2025Streaming Audio Generation from Discrete Tokens via Streaming Flow Matching
  47. NeurIPS 2025ThinkSound: Chain-of-Thought Reasoning in Multimodal LLMs for Audio Generation and Editing
  48. NeurIPS 2025Towards A Translative Model of Sperm Whale Vocalization
  49. NeurIPS 2025Unbiased Sliced Wasserstein Kernels for High-Quality Audio Captioning
  50. NeurIPS 2025Unifying Symbolic Music Arrangement: Track-Aware Reconstruction and Structured Tokenization

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