音频生成论文趋势 2023–2026

主要结论

• 音频生成论文从 2023 年的 32 篇增长到 2026 年的 136 篇，三年间扩大到约 4.3 倍。
• ICLR 是发音频生成论文最多的会议，2023–2026 年共 135 篇，占四个会议总量的 38%。
• 交叉方向里涨得最快的是应用 · computer vision：同时属于两个主题的论文从 2023 年的 0 篇增至 2026 年的 16 篇。
• 在「语音与音频」的 5 个主题里，它的 2026 年论文数排第 3；同组增长最快的视听学习是 1.8 倍，音频生成是 4.3 倍。

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

• NeurIPS 2026A Unified Audio Language Model with Text-Aligned Factorized Audio Tokenization
• ICML 2026PHALAR: Phasors for Learned Musical Audio Representations
• ICLR 2026AC-Foley: Reference-Audio-Guided Video-to-Audio Synthesis with Acoustic Transfer
• CVPR 2026AudioStory Generating Long-Form Narrative Audio with Large Language Models
• NeurIPS 2025🎧MOSPA: Human Motion Generation Driven by Spatial Audio
• ICML 2025Audio Flamingo 2: An Audio-Language Model with Long-Audio Understanding and Expert Reasoning Abilities
• ICLR 2025ARLON: Boosting Diffusion Transformers with Autoregressive Models for Long Video Generation
• CVPR 2025AudCast: Audio-Driven Human Video Generation by Cascaded Diffusion Transformers
• NeurIPS 2024Vocal Call Locator Benchmark (VCL) for localizing rodent vocalizations from multi-channel audio
• ICML 2024An Independence-promoting Loss for Music Generation with Language Models
• ICLR 2024Error Norm Truncation: Robust Training in the Presence of Data Noise for Text Generation Models
• CVPR 2024FlowVQTalker: High-Quality Emotional Talking Face Generation through Normalizing Flow and Quantization
• NeurIPS 2023High-Fidelity Audio Compression with Improved RVQGAN
• ICML 2023Make-An-Audio: Text-To-Audio Generation with Prompt-Enhanced Diffusion Models
• ICLR 2023AudioGen: Textually Guided Audio Generation
• CVPR 2023Conditional Generation of Audio From Video via Foley Analogies
• NeurIPS 2026AudioCALM: Continuous Autoregressive Language Modeling for Universal Audio Generation
• ICML 2026SonicMaster: Towards Controllable All-in-One Music Restoration and Mastering
• ICLR 2026AudioX: A Unified Framework for Anything-to-Audio Generation
• CVPR 2026Avatar Forcing Real-Time Interactive Head Avatar Generation for Natural Conversation

全部音频生成论文

共 116 篇，第 2 / 3 页

51. ICLR 2025MDSGen: Fast and Efficient Masked Diffusion Temporal-Aware Transformers for Open-Domain Sound Generation
52. ICLR 2025MVTokenFlow: High-quality 4D Content Generation using Multiview Token Flow
53. ICLR 2025PeriodWave: Multi-Period Flow Matching for High-Fidelity Waveform Generation
54. ICLR 2025Personalized Representation from Personalized Generation
55. ICLR 2025PianoMotion10M: Dataset and Benchmark for Hand Motion Generation in Piano Performance
56. ICLR 2025Presto! Distilling Steps and Layers for Accelerating Music Generation
57. ICLR 2025Provence: efficient and robust context pruning for retrieval-augmented generation
58. ICLR 2025Ready-to-React: Online Reaction Policy for Two-Character Interaction Generation
59. ICLR 2025RFWave: Multi-band Rectified Flow for Audio Waveform Reconstruction
60. ICLR 2025SCOPE: A Self-supervised Framework for Improving Faithfulness in Conditional Text Generation
61. ICLR 2025SiReRAG: Indexing Similar and Related Information for Multihop Reasoning
62. ICLR 2025SoundCTM: Unifying Score-based and Consistency Models for Full-band Text-to-Sound Generation
63. ICLR 2025Sports-Traj: A Unified Trajectory Generation Model for Multi-Agent Movement in Sports
64. ICLR 2025SSLAM: Enhancing Self-Supervised Models with Audio Mixtures for Polyphonic Soundscapes
65. ICLR 2025TabDiff: a Mixed-type Diffusion Model for Tabular Data Generation
66. ICLR 2025Talking Turns: Benchmarking Audio Foundation Models on Turn-Taking Dynamics
67. ICLR 2025TANGO: Co-Speech Gesture Video Reenactment with Hierarchical Audio Motion Embedding and Diffusion Interpolation
68. ICLR 2025The KoLMogorov Test: Compression by Code Generation
69. ICLR 2025Training-free Camera Control for Video Generation
70. ICLR 2025UniWav: Towards Unified Pre-training for Speech Representation Learning and Generation
71. ICLR 2025ViSAGe: Video-to-Spatial Audio Generation
72. ICLR 2025VLMaterial: Procedural Material Generation with Large Vision-Language Models
73. ICLR 2025Weakly Supervised Video Scene Graph Generation via Natural Language Supervision
74. ICLR 2025X-NeMo: Expressive Neural Motion Reenactment via Disentangled Latent Attention
75. ICML 2025ALMTokenizer: A Low-bitrate and Semantic-rich Audio Codec Tokenizer for Audio Language Modeling
76. ICML 2025Audio Flamingo 2: An Audio-Language Model with Long-Audio Understanding and Expert Reasoning Abilities
77. ICML 2025CodeSync: Synchronizing Large Language Models with Dynamic Code Evolution at Scale
78. ICML 2025Efficient Fine-Grained Guidance for Diffusion Model Based Symbolic Music Generation
79. ICML 2025ETTA: Elucidating the Design Space of Text-to-Audio Models
80. ICML 2025IMPACT: Iterative Mask-based Parallel Decoding for Text-to-Audio Generation with Diffusion Modeling
81. ICML 2025MuseControlLite: Multifunctional Music Generation with Lightweight Conditioners
82. ICML 2025OmniAudio: Generating Spatial Audio from 360-Degree Video
83. ICML 2025Sounding that Object: Interactive Object-Aware Image to Audio Generation
84. ICML 2025Supervised Contrastive Learning from Weakly-Labeled Audio Segments for Musical Version Matching
85. NeurIPS 2025🎧MOSPA: Human Motion Generation Driven by Spatial Audio
86. NeurIPS 2025AHa-Bench: Benchmarking Audio Hallucinations in Large Audio-Language Models
87. NeurIPS 2025Audio Flamingo 3: Advancing Audio Intelligence with Fully Open Large Audio Language Models
88. NeurIPS 2025Audio Super-Resolution with Latent Bridge Models
89. NeurIPS 2025Audio-Sync Video Generation with Multi-Stream Temporal Control
90. NeurIPS 2025AudSemThinker: Enhancing Audio-Language Models Through Reasoning over Semantics of Sound
91. NeurIPS 2025BNMusic: Blending Environmental Noises into Personalized Music
92. NeurIPS 2025BRACE: A Benchmark for Robust Audio Caption Quality Evaluation
93. NeurIPS 2025DroneAudioset: An Audio Dataset for Drone-based Search and Rescue
94. NeurIPS 2025Failure by Interference: Language Models Make Balanced Parentheses Errors When Faulty Mechanisms Overshadow Sound Ones
95. NeurIPS 2025Improving Target Sound Extraction via Disentangled Codec Representations with Privileged Knowledge Distillation
96. NeurIPS 2025JavisGPT: A Unified Multi-modal LLM for Sounding-Video Comprehension and Generation
97. NeurIPS 2025Let Them Talk: Audio-Driven Multi-Person Conversational Video Generation
98. NeurIPS 2025LeVo: High-Quality Song Generation with Multi-Preference Alignment
99. NeurIPS 2025Massive Sound Embedding Benchmark (MSEB)
100. NeurIPS 2025MEGADance: Mixture-of-Experts Architecture for Genre-Aware 3D Dance Generation

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。