1. Hifi-gan: Generative adversarial networks for efficient and high fidelity speech synthesis;kong;Advances in neural information processing systems,2020
2. UnivNet: A Neural Vocoder with Multi-Resolution Spectrogram Discriminators for High-Fidelity Waveform Generation
3. Learning features of music from scratch;thickstun,2016
4. Enabling factorized piano music modeling and generation with the maestro dataset;hawthorne,2018
5. Tfgan: Time and frequency domain based generative adversarial network for high-fidelity speech synthesis;tian,2020