@article{SpearTTS,
  title       = {Speak, Read and Prompt: High-Fidelity Text-to-Speech with Minimal Supervision},
  url         = {https://arxiv.org/abs/2302.03540},
  author      = {Kharitonov, Eugene and Vincent, Damien and Borsos, Zalán and Marinier, Raphaël and Girgin, Sertan and Pietquin, Olivier and Sharifi, Matt and Tagliasacchi, Marco and Zeghidour, Neil},
  publisher   = {arXiv},
  year        = {2023},
}

@article{MusicGen,
  title     = {Simple and Controllable Music Generation},
  url       = {https://arxiv.org/abs/2306.05284},
  author    = {Jade Copet and Felix Kreuk and Itai Gat and Tal Remez and David Kant and Gabriel Synnaeve and Yossi Adi and Alexandre Défossez},
  publisher = {arXiv},
  year      = {2023},
}

@article{Whisper,
  title     = {Robust Speech Recognition via Large-Scale Weak Supervision},
  url       = {https://arxiv.org/abs/2212.04356},
  author    = {Radford, Alec and Kim, Jong Wook and Xu, Tao and Brockman, Greg and McLeavey, Christine and Sutskever, Ilya},
  publisher = {arXiv},
  year      = {2022},
}

@article{EnCodec,
  title     = {High Fidelity Neural Audio Compression},
  url       = {https://arxiv.org/abs/2210.13438},
  author    = {Défossez, Alexandre and Copet, Jade and Synnaeve, Gabriel and Adi, Yossi},
  publisher = {arXiv},
  year      = {2022},
}

@article{Vocos,
  title     = {Vocos: Closing the Gap Between Time‑Domain and Fourier‑Based Neural Vocoders for High‑Quality Audio Synthesis},
  url       = {https://arxiv.org/abs/2306.00814},
  author    = {Hubert Siuzdak},
  publisher = {arXiv},
  year      = {2023},
}