WaveNet：《WaveNet: A Generative Model for Raw Audio》
Tacotron：《TACOTRON: Towards End-to-End Speech Synthesis》
Tacotron2：《Natural TTS Synthesis by Conditioning WaveNet on Mel Spectrogram Predictions》
HiFi-GAN：《HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesis》
VITS：《Conditional Variational Autoencoder with Adversarial Learning for End-toEnd Text-toSpeech》
标签：WaveNet,End,TTS,论文,汇总,HiFi,Speech,Synthesis From： https://www.cnblogs.com/zhaoke271828/p/16883956.html