% Key papers for Self-supervised speech representations (scime atlas, https://atlas.scime.ai). Authors are not included: add them from the paper pages.

@inproceedings{iclr2020_vq_29902,
  title = {{vq-wav2vec: Self-Supervised Learning of Discrete Speech Representations}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2020},
  url = {https://openreview.net/forum?id=rylwJxrYDS},
}

@inproceedings{icml2023_beats_41904,
  title = {{BEATs: Audio Pre-Training with Acoustic Tokenizers}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2023},
  url = {https://icml.cc/virtual/2023/poster/24937},
}

@inproceedings{iclr2024_mert_35563,
  title = {{MERT: Acoustic Music Understanding Model with Large-Scale Self-supervised Training}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2024},
  url = {https://iclr.cc/virtual/2024/poster/17510},
}

@inproceedings{icml2022_contentvec_40362,
  title = {{ContentVec: An Improved Self-Supervised Speech Representation by Disentangling Speakers}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2022},
  url = {https://icml.cc/virtual/2022/poster/18359},
}

@inproceedings{icml2022_self_41160,
  title = {{Self-Supervised Models of Audio Effectively Explain Human Cortical Responses to Speech}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2022},
  url = {https://icml.cc/virtual/2022/poster/18093},
}

@inproceedings{neurips2021_task_62300,
  title = {{Task Agnostic and Task Specific Self-Supervised Learning from Speech with LeBenchmark}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2021},
  url = {https://openreview.net/forum?id=TSvj5dmuSd},
}

@inproceedings{icml2023_efficient_42029,
  title = {{Efficient Self-supervised Learning with Contextualized Target Representations for Vision, Speech and Language}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2023},
  url = {https://icml.cc/virtual/2023/poster/25257},
}

@inproceedings{neurips2021_parp_62348,
  title = {{PARP: Prune, Adjust and Re-Prune for Self-Supervised Speech Recognition}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2021},
  url = {https://nips.cc/virtual/2021/poster/27940},
}

@inproceedings{neurips2023_dinosr_69762,
  title = {{DinoSR: Self-Distillation and Online Clustering for Self-supervised Speech Representation Learning}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2023},
  url = {https://nips.cc/virtual/2023/poster/70178},
}

@inproceedings{cvpr2022_sound_19901,
  title = {{Sound and Visual Representation Learning With Multiple Pretraining Tasks}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2022},
}

@inproceedings{icml2023_self_42303,
  title = {{Self-supervised Neural Factor Analysis for Disentangling Utterance-level Speech Representations}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2023},
  url = {https://icml.cc/virtual/2023/poster/24759},
}

@inproceedings{neurips2022_losses_63777,
  title = {{Losses Can Be Blessings: Routing Self-Supervised Speech Representations Towards Efficient Multilingual and Multitask Speech Processing}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2022},
  url = {https://nips.cc/virtual/2022/poster/53604},
}

@inproceedings{neurips2024_ca_72854,
  title = {{CA-SSLR: Condition-Aware Self-Supervised Learning Representation for Generalized Speech Processing}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/94546},
}

@inproceedings{iclr2024_multi_35101,
  title = {{Multi-resolution HuBERT: Multi-resolution Speech Self-Supervised Learning with Masked Unit Prediction}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2024},
  url = {https://iclr.cc/virtual/2024/poster/17972},
}

@inproceedings{icml2021_learning_39543,
  title = {{Learning de-identified representations of prosody from raw audio}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2021},
  url = {https://icml.cc/virtual/2021/poster/8805},
}

@inproceedings{icml2024_selfvc_43548,
  title = {{SelfVC: Voice Conversion With Iterative Refinement using Self Transformations}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2024},
  url = {https://icml.cc/virtual/2024/poster/34904},
}

@inproceedings{icml2026_bat_50129,
  title = {{BAT: Better Audio Transformer Guided by Convex Gated Probing}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2026},
  url = {https://openreview.net/forum?id=9DfsHAFE5l},
}

@inproceedings{neurips2025_closed_77581,
  title = {{Closed-Form Training Dynamics Reveal Learned Features and Linear Structure in Word2Vec-like Models}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2025},
  url = {https://openreview.net/forum?id=VS9N6q6b0k},
}

@inproceedings{iclr2025_sylber_81462,
  title = {{Sylber: Syllabic Embedding Representation of Speech from Raw Audio}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2025},
  url = {https://iclr.cc/virtual/2025/poster/30312},
}

@inproceedings{iclr2025_sslam_83469,
  title = {{SSLAM: Enhancing Self-Supervised Models with Audio Mixtures for Polyphonic Soundscapes}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2025},
  url = {https://iclr.cc/virtual/2025/poster/28347},
}

@inproceedings{iclr2026_unmute_85530,
  title = {{Unmute the Patch Tokens: Rethinking Probing in Multi-Label Audio Classification}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2026},
  url = {https://openreview.net/forum?id=FbY5Co2NWk},
}

@inproceedings{icml2024_speech_44965,
  title = {{Speech Self-Supervised Learning Using Diffusion Model Synthetic Data}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2024},
  url = {https://icml.cc/virtual/2024/poster/33487},
}

@inproceedings{icml2026_spear_55067,
  title = {{SPEAR: A Unified SSL Framework for Learning Speech and Audio Representations}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2026},
  url = {https://openreview.net/forum?id=vHaaDCLF0M},
}

@inproceedings{neurips2026_factorized_91293,
  title = {{Factorized Self-Supervised Speech Tokenization}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2026},
  url = {https://neurips.cc/virtual/2026/poster/149827},
}