@inproceedings{shen2018natural,
  title={Natural tts synthesis by conditioning wavenet on mel spectrogram predictions},
  author={Shen, Jonathan and Pang, Ruoming and Weiss, Ron J and Schuster, Mike and Jaitly, Navdeep and Yang, Zongheng and Chen, Zhifeng and Zhang, Yu and Wang, Yuxuan and Skerrv-Ryan, Rj and others},
  booktitle={2018 IEEE international conference on acoustics, speech and signal processing (ICASSP)},
  pages={4779--4783},
  year={2018},
  organization={IEEE}
}

@inproceedings{lancucki2021fastpitch,
  title={Fastpitch: Parallel text-to-speech with pitch prediction},
  author={{\L}a{\'n}cucki, Adrian},
  booktitle={ICASSP 2021-2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)},
  pages={6588--6592},
  year={2021},
  organization={IEEE}
}

@inproceedings{tatanov2022mixer,
  title={{Mixer-TTS}: non-autoregressive, fast and compact text-to-speech model conditioned on language model embeddings},
  author={Tatanov, Oktai and Beliaev, Stanislav and Ginsburg, Boris},
  booktitle={ICASSP 2022-2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)},
  pages={7482--7486},
  year={2022},
  organization={IEEE}
}

@inproceedings{shih2021rad,
  title={{RAD-TTS}: Parallel flow-based {TTS} with robust alignment learning and diverse synthesis},
  author={Shih, Kevin J and Valle, Rafael and Badlani, Rohan and Lancucki, Adrian and Ping, Wei and Catanzaro, Bryan},
  booktitle={ICML Workshop on Invertible Neural Networks, Normalizing Flows, and Explicit Likelihood Models},
  year={2021}
}

@article{kong2020hifi,
  title={{HiFi-GAN}: Generative adversarial networks for efficient and high fidelity speech synthesis},
  author={Kong, Jungil and Kim, Jaehyeon and Bae, Jaekyoung},
  journal={Advances in Neural Information Processing Systems},
  volume={33},
  pages={17022--17033},
  year={2020}
}

@inproceedings{prenger2019waveglow,
  title={Waveglow: A flow-based generative network for speech synthesis},
  author={Prenger, Ryan and Valle, Rafael and Catanzaro, Bryan},
  booktitle={ICASSP 2019-2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)},
  pages={3617--3621},
  year={2019},
  organization={IEEE}
}

@inproceedings{jang21_interspeech,
  author={Won Jang and Dan Lim and Jaesam Yoon and Bongwan Kim and Juntae Kim},
  title={{UnivNet: A Neural Vocoder with Multi-Resolution Spectrogram Discriminators for High-Fidelity Waveform Generation}},
  year=2021,
  booktitle={Proc. Interspeech 2021},
  pages={2207--2211},
  doi={10.21437/Interspeech.2021-1016}
}

@inproceedings{badlani2022one,
  title={One {TTS} alignment to rule them all},
  author={Badlani, Rohan and {\L}a{\'n}cucki, Adrian and Shih, Kevin J and Valle, Rafael and Ping, Wei and Catanzaro, Bryan},
  booktitle={ICASSP 2022-2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)},
  pages={6092--6096},
  year={2022},
  organization={IEEE}
}

@article{xue2021byt5,
  title={ByT5: Towards a token-free future with pre-trained byte-to-byte models 2021},
  author={Xue, Linting and Barua, Aditya and Constant, Noah and Al-Rfou, Rami and Narang, Sharan and Kale, Mihir and Roberts, Adam and Raffel, Colin},
  journal={arXiv preprint arXiv:2105.13626},
  year={2021}
}

@article{vrezavckova2021t5g2p,
  title={T5g2p: Using text-to-text transfer transformer for grapheme-to-phoneme conversion},
  author={{\v{R}}ez{\'a}{\v{c}}kov{\'a}, Mark{\'e}ta and {\v{S}}vec, Jan and Tihelka, Daniel},
  year={2021},
  journal={International Speech Communication Association}
}

@article{zhu2022byt5,
  title={ByT5 model for massively multilingual grapheme-to-phoneme conversion},
  author={Zhu, Jian and Zhang, Cong and Jurgens, David},
  journal={arXiv preprint arXiv:2204.03067},
  year={2022}
}

@article{ggulati2020conformer,
  title={Conformer: Convolution-augmented transformer for speech recognition},
  author={Gulati, Anmol and Qin, James and Chiu, Chung-Cheng and Parmar, Niki and Zhang, Yu and Yu, Jiahui and Han, Wei and Wang, Shibo and Zhang, Zhengdong and Wu, Yonghui and others},
  journal={arXiv preprint arXiv:2005.08100},
  year={2020}
}

@inproceedings{gorman2018improving,
  title={Improving homograph disambiguation with supervised machine learning},
  author={Gorman, Kyle and Mazovetskiy, Gleb and Nikolaev, Vitaly},
  booktitle={Proceedings of the Eleventh International Conference on Language Resources and Evaluation (LREC 2018)},
  year={2018}
}
@inproceedings{kim2021conditional,
  title={Conditional variational autoencoder with adversarial learning for end-to-end text-to-speech},
  author={Kim, Jaehyeon and Kong, Jungil and Son, Juhee},
  booktitle={International Conference on Machine Learning},
  pages={5530--5540},
  year={2021},
  organization={PMLR}
}

@article{zeghidour2022soundstream,
  author={Zeghidour, Neil and Luebs, Alejandro and Omran, Ahmed and Skoglund, Jan and Tagliasacchi, Marco},
  journal={IEEE/ACM Transactions on Audio, Speech, and Language Processing}, 
  title={{SoundStream}: An End-to-End Neural Audio Codec}, 
  year={2022},
  volume={30},
  pages={495-507},
  doi={10.1109/TASLP.2021.3129994}
}

@article{defossez2022encodec,
  title={High fidelity neural audio compression},
  author={D{\'e}fossez, Alexandre and Copet, Jade and Synnaeve, Gabriel and Adi, Yossi},
  journal={arXiv preprint arXiv:2210.13438},
  year={2022}
}

@article{mentzer2023finite,
  title={Finite scalar quantization: {VQ-VAE} made simple},
  author={Mentzer, Fabian and Minnen, David and Agustsson, Eirikur and Tschannen, Michael},
  journal={arXiv preprint arXiv:2309.15505},
  year={2023}
}