1. Deep learning using rectified linear units (ReLU);agarap;arXiv vol abs/1803 08375,2018
2. HiFi-GAN: Generative adversarial net-works for efficient and high fidelity speech synthesis;kong;Proc NeurIPS,2020
3. Controllable Neural Text-to-Speech Synthesis Using Intuitive Prosodic Features
4. Adam: A method for stochastic optimization;kingma;Proc ICLR San Diego,2015
5. Dropout: A simple way to prevent neural networks from over-fitting;srivastava;The Journal of Machine Learning Research,2014