% Key papers for Diffusion audio synthesis (scime atlas, https://atlas.scime.ai). Authors are not included: add them from the paper pages.

@inproceedings{iclr2017_samplernn_28331,
  title = {{SampleRNN: An Unconditional End-to-End Neural Audio Generation Model}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2017},
  url = {https://openreview.net/forum?id=SkxKPDv5xl},
}

@inproceedings{icml2017_neural_36303,
  title = {{Neural Audio Synthesis of Musical Notes with WaveNet Autoencoders}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2017},
  url = {https://icml.cc/virtual/2017/poster/868},
}

@inproceedings{aaai2022_diffsinger_1977,
  title = {{DiffSinger: Singing Voice Synthesis via Shallow Diffusion Mechanism}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2022},
  url = {https://aaai.org/papers/11020-diffsinger-singing-voice-synthesis-via-shallow-diffusion-mechanism/},
}

@inproceedings{cvpr2023_difftalk_20791,
  title = {{DiffTalk: Crafting Diffusion Models for Generalized Audio-Driven Portraits Animation}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2023},
  url = {https://cvpr.thecvf.com/virtual/2023/poster/22606},
}

@inproceedings{iclr2021_diffwave_30438,
  title = {{DiffWave: A Versatile Diffusion Model for Audio Synthesis}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2021},
  url = {https://iclr.cc/virtual/2021/poster/2979},
}

@inproceedings{cvpr2023_taming_22305,
  title = {{Taming Diffusion Models for Audio-Driven Co-Speech Gesture Generation}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2023},
  url = {https://cvpr.thecvf.com/virtual/2023/poster/23264},
}

@inproceedings{neurips2023_high_69589,
  title = {{High-Fidelity Audio Compression with Improved RVQGAN}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2023},
  url = {https://nips.cc/virtual/2023/poster/70342},
}

@inproceedings{icml2023_audioldm_41615,
  title = {{AudioLDM: Text-to-Audio Generation with Latent Diffusion Models}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2023},
  url = {https://icml.cc/virtual/2023/poster/24145},
}

@inproceedings{iclr2020_ddsp_29265,
  title = {{DDSP: Differentiable Digital Signal Processing}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2020},
  url = {https://openreview.net/forum?id=B1x1ma4tDr},
}

@inproceedings{iclr2019_clarinet_28947,
  title = {{ClariNet: Parallel Wave Generation in End-to-End Text-to-Speech}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2019},
  url = {https://iclr.cc/virtual/2019/poster/680},
}

@inproceedings{aaai2019_ai_101254,
  title = {{AI-Sketcher : A Deep Generative Model for Producing High-Quality Sketches}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2019},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/4103},
}

@inproceedings{iclr2023_audiogen_32237,
  title = {{AudioGen: Textually Guided Audio Generation}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2023},
  url = {https://iclr.cc/virtual/2023/poster/11521},
}

@inproceedings{cvpr2024_seeing_24768,
  title = {{Seeing and Hearing: Open-domain Visual-Audio Generation with Diffusion Latent Aligners}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/31506},
}

@inproceedings{neurips2022_binauralgrad_65326,
  title = {{BinauralGrad: A Two-Stage Conditional Diffusion Probabilistic Model for Binaural Audio Synthesis}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2022},
  url = {https://nips.cc/virtual/2022/poster/53453},
}

@inproceedings{neurips2023_any_66663,
  title = {{Any-to-Any Generation via Composable Diffusion}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2023},
  url = {https://nips.cc/virtual/2023/poster/72964},
}

@inproceedings{neurips2018_sing_57591,
  title = {{SING: Symbol-to-Instrument Neural Generator}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2018},
  url = {https://nips.cc/virtual/2018/poster/11862},
}

@inproceedings{neurips2020_a_59273,
  title = {{A Spectral Energy Distance for Parallel Speech Synthesis}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2020},
  url = {https://nips.cc/virtual/2020/poster/17831},
}

@inproceedings{iclr2024_separate_34549,
  title = {{Separate and Diffuse: Using a Pretrained Diffusion Model for Better Source Separation}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2024},
  url = {https://iclr.cc/virtual/2024/poster/18525},
}

@inproceedings{iclr2024_vocos_35543,
  title = {{Vocos: Closing the gap between time-domain and Fourier-based neural vocoders for high-quality audio synthesis}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2024},
  url = {https://iclr.cc/virtual/2024/poster/17530},
}

@inproceedings{aaai2021_audio_160,
  title = {{Audio-Visual Localization by Synthetic Acoustic Image Generation}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2021},
  url = {https://aaai.org/papers/02523-audio-visual-localization-by-synthetic-acoustic-image-generation/},
}

@inproceedings{iclr2024_an_35392,
  title = {{An Efficient Membership Inference Attack for the Diffusion Model by Proximal Initialization}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2024},
  url = {https://iclr.cc/virtual/2024/poster/17681},
}

@inproceedings{iclr2024_multi_34964,
  title = {{Multi-Source Diffusion Models for Simultaneous Music Generation and Separation}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2024},
  url = {https://iclr.cc/virtual/2024/poster/18110},
}

@inproceedings{icml2024_fast_45141,
  title = {{Fast Timing-Conditioned Latent Audio Diffusion}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2024},
  url = {https://icml.cc/virtual/2024/poster/33311},
}

@inproceedings{aaai2024_regeneration_7090,
  title = {{Regeneration Learning: A Learning Paradigm for Data Generation}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/30271},
}

@inproceedings{cvpr2025_enhancing_26136,
  title = {{Enhancing Dance-to-Music Generation via Negative Conditioning Latent Diffusion Model}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/32817},
}

@inproceedings{aaai2026_pase_108210,
  title = {{PASE: Leveraging the Phonological Prior of WavLM for Low-Hallucination Generative Speech Enhancement}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2026},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/40562},
}

@inproceedings{iclr2024_masked_34315,
  title = {{Masked Audio Generation using a Single Non-Autoregressive Transformer}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2024},
  url = {https://iclr.cc/virtual/2024/poster/18760},
}

@inproceedings{iclr2024_diffar_34046,
  title = {{DiffAR: Denoising Diffusion Autoregressive Model for Raw Speech Waveform Generation}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2024},
  url = {https://iclr.cc/virtual/2024/poster/19029},
}

@inproceedings{neurips2025_mge_74781,
  title = {{MGE-LDM: Joint Latent Diffusion for Simultaneous Music Generation and Source Extraction}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2025},
  url = {https://openreview.net/forum?id=17O8DqToyr},
}

@inproceedings{icml2025_ditar_46303,
  title = {{DiTAR: Diffusion Transformer Autoregressive Modeling for Speech Generation}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2025},
  url = {https://icml.cc/virtual/2025/poster/46258},
}

@inproceedings{icml2026_optimality_49267,
  title = {{Optimality of FSQ Tokens for Continuous Diffusion for Categorical Data with Application to Text-to-Speech}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2026},
  url = {https://openreview.net/forum?id=0uS3P0Dlh9},
}

@inproceedings{icml2026_regen_52144,
  title = {{ReGen: Hierarchical Multi-Prompt Representation Generation for Efficient Waveform Diffusion Models}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2026},
  url = {https://openreview.net/forum?id=T8Y9elIrXa},
}

@inproceedings{neurips2025_bnmusic_76339,
  title = {{BNMusic: Blending Environmental Noises into Personalized Music}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2025},
  url = {https://openreview.net/forum?id=IIgVYnadfR},
}

@inproceedings{neurips2025_zerosep_76341,
  title = {{ZeroSep: Separate Anything in Audio with Zero Training}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2025},
  url = {https://openreview.net/forum?id=IIjiNTR1cV},
}

@inproceedings{neurips2025_robust_77864,
  title = {{Robust Distortion-Free Watermark for Autoregressive Audio Generation Models}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2025},
  url = {https://openreview.net/forum?id=YLlpF71IZJ},
}

@inproceedings{neurips2025_can_79895,
  title = {{Can Diffusion Models Disentangle? A Theoretical Perspective}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2025},
  url = {https://openreview.net/forum?id=u1HclHIsLQ},
}

@inproceedings{iclr2025_synthio_82687,
  title = {{Synthio: Augmenting Small-Scale Audio Classification Datasets with Synthetic Data}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2025},
  url = {https://iclr.cc/virtual/2025/poster/29111},
}