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

@inproceedings{aaai2024_audiogpt_5225,
  title = {{AudioGPT: Understanding and Generating Speech, Music, Sound, and Talking Head}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/30570},
}

@inproceedings{aaai2021_dialogbert_423,
  title = {{DialogBERT: Discourse-Aware Response Generation via Learning to Recover and Rank Utterances}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2021},
  url = {https://aaai.org/papers/12911-dialogbert-discourse-aware-response-generation-via-learning-to-recover-and-rank-utterances/},
}

@inproceedings{aaai2022_towards_2853,
  title = {{Towards Building ASR Systems for the Next Billion Users}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2022},
  url = {https://aaai.org/papers/10813-towards-building-asr-systems-for-the-next-billion-users/},
}

@inproceedings{aaai2025_codec_8443,
  title = {{Codec Does Matter: Exploring the Semantic Shortcoming of Codec for Audio Language Model}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/34761},
}

@inproceedings{neurips2023_hyporadise_68741,
  title = {{HyPoradise: An Open Baseline for Generative Speech Recognition with Large Language Models}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2023},
  url = {https://nips.cc/virtual/2023/poster/73533},
}

@inproceedings{aaai2021_synchronous_1453,
  title = {{Synchronous Interactive Decoding for Multilingual Neural Machine Translation}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2021},
  url = {https://aaai.org/papers/12981-synchronous-interactive-decoding-for-multilingual-neural-machine-translation/},
}

@inproceedings{neurips2024_sd_72030,
  title = {{SD-Eval: A Benchmark Dataset for Spoken Dialogue Understanding Beyond Words}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/97707},
}

@inproceedings{aaai2025_language_9699,
  title = {{Language Model Can Listen While Speaking}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/34665},
}

@inproceedings{neurips2023_textually_68314,
  title = {{Textually Pretrained Speech Language Models}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2023},
  url = {https://nips.cc/virtual/2023/poster/71490},
}

@inproceedings{aaai2025_medsage_9843,
  title = {{MEDSAGE: Enhancing Robustness of Medical Dialogue Summarization to ASR Errors with LLM-generated Synthetic Dialogues}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/34518},
}

@inproceedings{aaai2025_speech_10815,
  title = {{Speech Recognition Meets Large Language Model: Benchmarking, Models, and Exploration}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/34666},
}

@inproceedings{iclr2025_naturelm_83034,
  title = {{NatureLM-audio: an Audio-Language Foundation Model for Bioacoustics}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2025},
  url = {https://iclr.cc/virtual/2025/poster/28770},
}

@inproceedings{iclr2024_polyvoice_34968,
  title = {{PolyVoice: Language Models for Speech to Speech Translation}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2024},
  url = {https://iclr.cc/virtual/2024/poster/18106},
}

@inproceedings{icml2024_audio_44593,
  title = {{Audio Flamingo: A Novel Audio Language Model with Few-Shot Learning and Dialogue Abilities}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2024},
  url = {https://icml.cc/virtual/2024/poster/33859},
}

@inproceedings{icml2025_freeze_48768,
  title = {{Freeze-Omni: A Smart and Low Latency Speech-to-speech Dialogue Model with Frozen LLM}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2025},
  url = {https://icml.cc/virtual/2025/poster/43854},
}

@inproceedings{neurips2024_a_72699,
  title = {{A Full-duplex Speech Dialogue Scheme Based On Large Language Model}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/94688},
}

@inproceedings{iclr2024_large_34789,
  title = {{Large Language Models are Efficient Learners of Noise-Robust Speech Recognition}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2024},
  url = {https://iclr.cc/virtual/2024/poster/18285},
}

@inproceedings{neurips2023_spokenwoz_69859,
  title = {{SpokenWOZ: A Large-Scale Speech-Text Benchmark for Spoken Task-Oriented Dialogue Agents}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2023},
  url = {https://nips.cc/virtual/2023/poster/73427},
}

@inproceedings{neurips2024_indicvoices_70388,
  title = {{IndicVoices-R: Unlocking a Massive Multilingual Multi-speaker Speech Corpus for Scaling Indian TTS}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/97858},
}

@inproceedings{neurips2024_uniaudio_71845,
  title = {{UniAudio 1.5: Large Language Model-Driven Audio Codec is A Few-Shot Audio Task Learner}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/95454},
}

@inproceedings{neurips2025_mmar_78524,
  title = {{MMAR: A Challenging Benchmark for Deep Reasoning in Speech, Audio, Music, and Their Mix}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2025},
  url = {https://openreview.net/forum?id=fgmrBJemlQ},
}

@inproceedings{aaai2024_allot_7859,
  title = {{“Allot?” is “A Lot!” Towards Developing More Generalized Speech Recognition System for Accessible Communication}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/30381},
}

@inproceedings{aaai2025_enhancing_8959,
  title = {{Enhancing Entertainment Translation for Indian Languages Using Adaptive Context, Style and LLMs}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/34698},
}

@inproceedings{aaai2025_recording_10485,
  title = {{Recording for Eyes, Not Echoing to Ears: Contextualized Spoken-to-Written Conversion of ASR Transcripts}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/34642},
}

@inproceedings{cvpr2025_llm_26696,
  title = {{LLM-driven Multimodal and Multi-Identity Listening Head Generation}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/33440},
}

@inproceedings{neurips2024_ssdm_71517,
  title = {{SSDM: Scalable Speech Dysfluency Modeling}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/95746},
}