Audio-text Model¶

@misc{chu2024qwen2audiotechnicalreport,
      title={Qwen2-Audio Technical Report},
      author={Yunfei Chu and Jin Xu and Qian Yang and Haojie Wei and Xipin Wei and Zhifang Guo and Yichong Leng and Yuanjun Lv and Jinzheng He and Junyang Lin and Chang Zhou and Jingren Zhou},
      year={2024},
      eprint={2407.10759},
      archivePrefix={arXiv},
      primaryClass={eess.AS},
      url={https://arxiv.org/abs/2407.10759},
}

@inproceedings{goel2025audioflamingo3,
  archiveprefix = {arXiv},
  author = {Arushi Goel and Sreyan Ghosh and Jaehyeon Kim and Sonal Kumar and Zhifeng Kong and Sang-gil Lee and Chao-Han Huck Yang and Ramani Duraiswami and Dinesh Manocha and Rafael Valle and Bryan Catanzaro},
  booktitle = {The Thirty-ninth Annual Conference on Neural Information Processing Systems},
  eprint = {2507.08128},
  title = {Audio Flamingo 3: Advancing Audio Intelligence with Fully Open Large Audio Language Models},
  url = {https://openreview.net/forum?id=FjByDpDVIO},
  year = {2025},
}

@inproceedings{zhu2024languagebind,
  archiveprefix = {arXiv},
  author = {Bin Zhu and Bin Lin and Munan Ning and Yang Yan and Jiaxi Cui and WANG HongFa and Yatian Pang and Wenhao Jiang and Junwu Zhang and Zongwei Li and Cai Wan Zhang and Zhifeng Li and Wei Liu and Li Yuan},
  booktitle = {The Twelfth International Conference on Learning Representations},
  eprint = {2310.01852},
  title = {LanguageBind: Extending Video-Language Pretraining to N-modality by Language-based Semantic Alignment},
  url = {https://openreview.net/forum?id=QmZKc7UZCy},
  year = {2024},
}

@article{zhu2025muqselfsupervisedmusicrepresentation,
  author = {Zhu, Haina and Zhou, Yizhi and Chen, Hangting and Yu, Jianwei and Ma, Ziyang and Gu, Rongzhi and Luo, Yi and Tan, Wei and Chen, Xie},
  doi = {10.1109/taslpro.2025.3602320},
  issn = {2998-4173},
  journal = {IEEE Transactions on Audio, Speech and Language Processing},
  pages = {3653–3664},
  publisher = {Institute of Electrical and Electronics Engineers (IEEE)},
  title = {MuQ: Self-Supervised Music Representation Learning With Mel Residual Vector Quantization},
  url = {https://doi.org/10.1109/taslpro.2025.3602320},
  volume = {33},
  year = {2025},
}

@inproceedings{wu2024largescalecontrastivelanguageaudiopretraining,
  author = {Wu, Yusong and Chen, Ke and Zhang, Tianyu and Hui, Yuchen and Berg-Kirkpatrick, Taylor and Dubnov, Shlomo},
  booktitle = {ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)},
  doi = {10.1109/icassp49357.2023.10095969},
  month = {June},
  pages = {1–5},
  publisher = {IEEE},
  title = {Large-Scale Contrastive Language-Audio Pretraining with Feature Fusion and Keyword-to-Caption Augmentation},
  url = {https://doi.org/10.1109/icassp49357.2023.10095969},
  year = {2023},
}

@inproceedings{wu2024largescalecontrastivelanguageaudiopretraining,
  author = {Wu, Yusong and Chen, Ke and Zhang, Tianyu and Hui, Yuchen and Berg-Kirkpatrick, Taylor and Dubnov, Shlomo},
  booktitle = {ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)},
  doi = {10.1109/icassp49357.2023.10095969},
  month = {June},
  pages = {1–5},
  publisher = {IEEE},
  title = {Large-Scale Contrastive Language-Audio Pretraining with Feature Fusion and Keyword-to-Caption Augmentation},
  url = {https://doi.org/10.1109/icassp49357.2023.10095969},
  year = {2023},
}

@inproceedings{wu2024largescalecontrastivelanguageaudiopretraining,
  author = {Wu, Yusong and Chen, Ke and Zhang, Tianyu and Hui, Yuchen and Berg-Kirkpatrick, Taylor and Dubnov, Shlomo},
  booktitle = {ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)},
  doi = {10.1109/icassp49357.2023.10095969},
  month = {June},
  pages = {1–5},
  publisher = {IEEE},
  title = {Large-Scale Contrastive Language-Audio Pretraining with Feature Fusion and Keyword-to-Caption Augmentation},
  url = {https://doi.org/10.1109/icassp49357.2023.10095969},
  year = {2023},
}

@inproceedings{wu2024largescalecontrastivelanguageaudiopretraining,
  author = {Wu, Yusong and Chen, Ke and Zhang, Tianyu and Hui, Yuchen and Berg-Kirkpatrick, Taylor and Dubnov, Shlomo},
  booktitle = {ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)},
  doi = {10.1109/icassp49357.2023.10095969},
  month = {June},
  pages = {1–5},
  publisher = {IEEE},
  title = {Large-Scale Contrastive Language-Audio Pretraining with Feature Fusion and Keyword-to-Caption Augmentation},
  url = {https://doi.org/10.1109/icassp49357.2023.10095969},
  year = {2023},
}

@inproceedings{wu2024largescalecontrastivelanguageaudiopretraining,
  author = {Wu, Yusong and Chen, Ke and Zhang, Tianyu and Hui, Yuchen and Berg-Kirkpatrick, Taylor and Dubnov, Shlomo},
  booktitle = {ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)},
  doi = {10.1109/icassp49357.2023.10095969},
  month = {June},
  pages = {1–5},
  publisher = {IEEE},
  title = {Large-Scale Contrastive Language-Audio Pretraining with Feature Fusion and Keyword-to-Caption Augmentation},
  url = {https://doi.org/10.1109/icassp49357.2023.10095969},
  year = {2023},
}

@inproceedings{wu2022wav2cliplearningrobustaudio,
  author = {Wu, Ho-Hsiang and Seetharaman, Prem and Kumar, Kundan and Bello, Juan Pablo},
  booktitle = {ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)},
  doi = {10.1109/icassp43922.2022.9747669},
  month = {May},
  pages = {4563–4567},
  publisher = {IEEE},
  title = {Wav2CLIP: Learning Robust Audio Representations from Clip},
  url = {https://doi.org/10.1109/icassp43922.2022.9747669},
  year = {2022},
}

@inproceedings{CLAP2022,
  title={Clap learning audio concepts from natural language supervision},
  author={Elizalde, Benjamin and Deshmukh, Soham and Al Ismail, Mahmoud and Wang, Huaming},
  booktitle={ICASSP 2023-2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)},
  pages={1--5},
  year={2023},
  organization={IEEE}
}

@inproceedings{CLAP2023,
  author = {Elizalde, Benjamin and Deshmukh, Soham and Wang, Huaming},
  booktitle = {ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)},
  doi = {10.1109/icassp48485.2024.10448504},
  month = {Apr},
  pages = {336–340},
  publisher = {IEEE},
  title = {Natural Language Supervision For General-Purpose Audio Representations},
  url = {https://doi.org/10.1109/icassp48485.2024.10448504},
  year = {2024},
}

@inproceedings{ao2022speecht5unifiedmodalencoderdecoderpretraining,
  address = {Dublin, Ireland},
  author = {Ao, Junyi and Wang, Rui and Zhou, Long and Wang, Chengyi and Ren, Shuo and Wu, Yu and Liu, Shujie and Ko, Tom and Li, Qing and Zhang, Yu and Wei, Zhihua and Qian, Yao and Li, Jinyu and Wei, Furu},
  booktitle = {Proceedings of the 60th Annual Meeting of the {A}ssociation for {C}omputational {L}inguistics (Volume 1: Long Papers)},
  doi = {10.18653/v1/2022.acl-long.393},
  editor = {Muresan, Smaranda and Nakov, Preslav and Villavicencio, Aline},
  month = {may},
  pages = {5723--5738},
  publisher = {Association for Computational Linguistics},
  title = {{S}peech{T}5: Unified-Modal Encoder-Decoder Pre-Training for Spoken Language Processing},
  url = {https://aclanthology.org/2022.acl-long.393/},
  year = {2022},
}