% Key papers for Neural text-to-speech synthesis (scime atlas, https://atlas.scime.ai). Authors are not included: add them from the paper pages.

@inproceedings{neurips2019_fastspeech_58272,
  title = {{FastSpeech: Fast, Robust and Controllable Text to Speech}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2019},
  url = {https://nips.cc/virtual/2019/poster/13497},
}

@inproceedings{neurips2017_deep_56249,
  title = {{Deep Voice 2: Multi-Speaker Neural Text-to-Speech}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2017},
  url = {https://nips.cc/virtual/2017/poster/9081},
}

@inproceedings{neurips2020_glow_59952,
  title = {{Glow-TTS: A Generative Flow for Text-to-Speech via Monotonic Alignment Search}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2020},
  url = {https://nips.cc/virtual/2020/poster/17587},
}

@inproceedings{cvpr2020_learning_15763,
  title = {{Learning Individual Speaking Styles for Accurate Lip to Speech Synthesis}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2020},
}

@inproceedings{iclr2021_flowtron_30170,
  title = {{Flowtron: an Autoregressive Flow-based Generative Network for Text-to-Speech Synthesis}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2021},
  url = {https://iclr.cc/virtual/2021/poster/3204},
}

@inproceedings{icml2017_dual_36166,
  title = {{Dual Supervised Learning}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2017},
  url = {https://icml.cc/virtual/2017/poster/763},
}

@inproceedings{cvpr2024_diffsheg_23189,
  title = {{DiffSHEG: A Diffusion-Based Approach for Real-Time Speech-driven Holistic 3D Expression and Gesture Generation}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/30816},
}

@inproceedings{cvpr2023_qpgesture_21952,
  title = {{QPGesture: Quantization-Based and Phase-Guided Motion Matching for Natural Speech-Driven Gesture Generation}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2023},
  url = {https://cvpr.thecvf.com/virtual/2023/poster/21695},
}

@inproceedings{icml2021_meta_39607,
  title = {{Meta-StyleSpeech : Multi-Speaker Adaptive Text-to-Speech Generation}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2021},
  url = {https://icml.cc/virtual/2021/poster/9659},
}

@inproceedings{neurips2023_voicebox_69060,
  title = {{Voicebox: Text-Guided Multilingual Universal Speech Generation at Scale}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2023},
  url = {https://nips.cc/virtual/2023/poster/70815},
}

@inproceedings{iclr2019_hierarchical_29217,
  title = {{Hierarchical Generative Modeling for Controllable Speech Synthesis}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2019},
  url = {https://iclr.cc/virtual/2019/poster/754},
}

@inproceedings{iclr2024_naturalspeech_34438,
  title = {{NaturalSpeech 2: Latent Diffusion Models are Natural and Zero-Shot Speech and Singing Synthesizers}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2024},
  url = {https://iclr.cc/virtual/2024/poster/18637},
}

@inproceedings{cvpr2024_emotional_23359,
  title = {{Emotional Speech-driven 3D Body Animation via Disentangled Latent Diffusion}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/30170},
}

@inproceedings{iclr2021_end_30673,
  title = {{End-to-end Adversarial Text-to-Speech}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2021},
  url = {https://iclr.cc/virtual/2021/poster/2778},
}

@inproceedings{aaai2023_a_3032,
  title = {{A Vector Quantized Approach for Text to Speech Synthesis on Real-World Spontaneous Speech}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2023},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/26488},
}

@inproceedings{aaai2024_unicats_7694,
  title = {{UniCATS: A Unified Context-Aware Text-to-Speech Framework with Contextual VQ-Diffusion and Vocoding}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/29747},
}

@inproceedings{neurips2021_noresqa_62242,
  title = {{NORESQA: A Framework for Speech Quality Assessment using Non-Matching References}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2021},
  url = {https://nips.cc/virtual/2021/poster/27147},
}

@inproceedings{neurips2023_styletts_69336,
  title = {{StyleTTS 2: Towards Human-Level Text-to-Speech through Style Diffusion and Adversarial Training with Large Speech Language Models}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2023},
  url = {https://nips.cc/virtual/2023/poster/70566},
}

@inproceedings{icml2022_translatotron_41293,
  title = {{Translatotron 2: High-quality direct speech-to-speech translation with voice preservation}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2022},
  url = {https://icml.cc/virtual/2022/poster/16401},
}

@inproceedings{icml2024_naturalspeech_44900,
  title = {{NaturalSpeech 3: Zero-Shot Speech Synthesis with Factorized Codec and Diffusion Models}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2024},
  url = {https://icml.cc/virtual/2024/poster/33552},
}

@inproceedings{cvpr2024_faces_23444,
  title = {{Faces that Speak: Jointly Synthesising Talking Face and Speech from Text}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/31880},
}

@inproceedings{aaai2025_techsinger_10935,
  title = {{TechSinger: Technique Controllable Multilingual Singing Voice Synthesis via Flow Matching}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/34571},
}

@inproceedings{cvpr2025_retrieving_27455,
  title = {{Retrieving Semantics from the Deep: an RAG Solution for Gesture Synthesis}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/33342},
}

@inproceedings{aaai2026_indextts2_108468,
  title = {{IndexTTS2: A Breakthrough in Emotionally Expressive and Duration-Controlled Auto-Regressive Zero-Shot Text-to-Speech}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2026},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/40820},
}

@inproceedings{aaai2024_let_6519,
  title = {{Let There Be Sound: Reconstructing High Quality Speech from Silent Videos}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/28055},
}

@inproceedings{neurips2024_covomix_72454,
  title = {{CoVoMix: Advancing Zero-Shot Speech Generation for Human-like Multi-talker Conversations}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/94904},
}

@inproceedings{aaai2025_emoreg_8934,
  title = {{EmoReg: Directional Latent Vector Modeling for Emotional Intensity Regularization in Diffusion-based Voice Conversion}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/34569},
}

@inproceedings{neurips2025_covomix2_74741,
  title = {{CoVoMix2: Advancing Zero-Shot Dialogue Generation with Fully Non-Autoregressive Flow Matching}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2025},
  url = {https://openreview.net/forum?id=0fq8vYOnxi},
}

@inproceedings{iclr2024_generative_34190,
  title = {{Generative Pre-training for Speech with Flow Matching}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2024},
  url = {https://iclr.cc/virtual/2024/poster/18885},
}

@inproceedings{icml2025_emotional_46651,
  title = {{Emotional Face-to-Speech}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2025},
  url = {https://icml.cc/virtual/2025/poster/45920},
}

@inproceedings{icml2025_etta_47724,
  title = {{ETTA: Elucidating the Design Space of Text-to-Audio Models}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2025},
  url = {https://icml.cc/virtual/2025/poster/44876},
}

@inproceedings{icml2025_dmospeech_48573,
  title = {{DMOSpeech: Direct Metric Optimization via Distilled Diffusion Model in Zero-Shot Speech Synthesis}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2025},
  url = {https://icml.cc/virtual/2025/poster/44048},
}

@inproceedings{neurips2025_mooncast_76731,
  title = {{MoonCast: High-Quality Zero-Shot Podcast Generation}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2025},
  url = {https://openreview.net/forum?id=MVlKSYR7HX},
}

@inproceedings{neurips2025_tadicodec_80115,
  title = {{TaDiCodec: Text-aware Diffusion Speech Tokenizer for Speech Language Modeling}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2025},
  url = {https://openreview.net/forum?id=wHsFqmM1rp},
}

@inproceedings{iclr2025_maskgct_81396,
  title = {{MaskGCT: Zero-Shot Text-to-Speech with Masked Generative Codec Transformer}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2025},
  url = {https://iclr.cc/virtual/2025/poster/30376},
}