Audio Generation papers, 2023–2026

Key findings

• Audio Generation went from 32 papers in 2023 to 136 in 2026, roughly 4.3x in three years.
• ICLR publishes the most Audio Generation work: 135 papers from 2023 to 2026, 38% of the four-venue total.
• The fastest-growing overlap is with Applications · computer vision: papers tagged with both rose from 0 in 2023 to 16 in 2026.
• Among the 5 topics under Audio and Speech, it ranks #3 by 2026 paper count; the fastest grower in the group, Audio-Visual Learning, is up 1.8x versus 4.3x here.

Representative papers

Spread across years and venues so every edition shows up

• 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

All Audio Generation papers

32 papers, page 1 of 1

1. NeurIPS 2025🎧MOSPA: Human Motion Generation Driven by Spatial Audio
2. NeurIPS 2025AHa-Bench: Benchmarking Audio Hallucinations in Large Audio-Language Models
3. NeurIPS 2025Audio Flamingo 3: Advancing Audio Intelligence with Fully Open Large Audio Language Models
4. NeurIPS 2025Audio Super-Resolution with Latent Bridge Models
5. NeurIPS 2025Audio-Sync Video Generation with Multi-Stream Temporal Control
6. NeurIPS 2025AudSemThinker: Enhancing Audio-Language Models Through Reasoning over Semantics of Sound
7. NeurIPS 2025BNMusic: Blending Environmental Noises into Personalized Music
8. NeurIPS 2025BRACE: A Benchmark for Robust Audio Caption Quality Evaluation
9. NeurIPS 2025DroneAudioset: An Audio Dataset for Drone-based Search and Rescue
10. NeurIPS 2025Failure by Interference: Language Models Make Balanced Parentheses Errors When Faulty Mechanisms Overshadow Sound Ones
11. NeurIPS 2025Improving Target Sound Extraction via Disentangled Codec Representations with Privileged Knowledge Distillation
12. NeurIPS 2025JavisGPT: A Unified Multi-modal LLM for Sounding-Video Comprehension and Generation
13. NeurIPS 2025Let Them Talk: Audio-Driven Multi-Person Conversational Video Generation
14. NeurIPS 2025LeVo: High-Quality Song Generation with Multi-Preference Alignment
15. NeurIPS 2025Massive Sound Embedding Benchmark (MSEB)
16. NeurIPS 2025MEGADance: Mixture-of-Experts Architecture for Genre-Aware 3D Dance Generation
17. NeurIPS 2025MGE-LDM: Joint Latent Diffusion for Simultaneous Music Generation and Source Extraction
18. NeurIPS 2025MoCha: Towards Movie-Grade Talking Character Generation
19. NeurIPS 2025Model-Guided Dual-Role Alignment for High-Fidelity Open-Domain Video-to-Audio Generation
20. NeurIPS 2025MRSAudio: A Large-Scale Multimodal Recorded Spatial Audio Dataset with Refined Annotations
21. NeurIPS 2025OmniTalker: One-shot Real-time Text-Driven Talking Audio-Video Generation With Multimodal Style Mimicking
22. NeurIPS 2025Resounding Acoustic Fields with Reciprocity
23. NeurIPS 2025Robust Distortion-Free Watermark for Autoregressive Audio Generation Models
24. NeurIPS 2025SAO-Instruct: Free-form Audio Editing using Natural Language Instructions
25. NeurIPS 2025SongBloom: Coherent Song Generation via Interleaved Autoregressive Sketching and Diffusion Refinement
26. NeurIPS 2025Streaming Audio Generation from Discrete Tokens via Streaming Flow Matching
27. NeurIPS 2025ThinkSound: Chain-of-Thought Reasoning in Multimodal LLMs for Audio Generation and Editing
28. NeurIPS 2025Towards A Translative Model of Sperm Whale Vocalization
29. NeurIPS 2025Unbiased Sliced Wasserstein Kernels for High-Quality Audio Captioning
30. NeurIPS 2025Unifying Symbolic Music Arrangement: Track-Aware Reconstruction and Structured Tokenization
31. NeurIPS 2025VASA-3D: Lifelike Audio-Driven Gaussian Head Avatars from a Single Image
32. NeurIPS 2025VITA-Audio: Fast Interleaved Audio-Text Token Generation for Efficient Large Speech-Language Model

FAQ

How many Audio Generation papers were published at NeurIPS, ICLR, ICML and CVPR from 2023 to 2026?

357 in total: 32 in 2023, 73 in 2024, 116 in 2025, 136 in 2026.

How many Audio Generation papers are at NeurIPS 2026?

NeurIPS 2026 has 21 Audio Generation papers, versus 32 the year before.

How many Audio Generation papers are at ICLR 2026?

ICLR 2026 has 64 Audio Generation papers, versus 43 the year before.

How many Audio Generation papers are at ICML 2026?

ICML 2026 has 25 Audio Generation papers, versus 10 the year before.

How many Audio Generation papers are at CVPR 2026?

CVPR 2026 has 26 Audio Generation papers, versus 31 the year before.

Which conference publishes the most Audio Generation papers?

ICLR, with 135 papers from 2023 to 2026.