Let IT Begin

SC-GlowTTS: An Efficient Zero-Shot Multi-Speaker Text-to-Speech Model Unseen speaker에 대한 similarity를 향상하는 zero-shot text-to-speech 모델이 필요함 SC-GlowTTS Flow-based decoder를 기반으로 speaker-conditional architecture를 도입 Text encoder로써 dilated residual convolutional-based encoder, gated convolutional-based encoder, transformer-based enocoder를 비교 추가적으로 text-to-speech 모델을 통해 예측된 spectrogram에 대해 GAN-based v..