반응형
[Paper 리뷰] Multi-SpectroGAN: High-Diversity and High-Fidelity Spectrogram Generation with Adversarial Style Combination for Speech Synthesis
Multi-SpectroGAN: High-Diversity and High-Fidelity Spectrogram Generation with Adversarial Style Combination for Speech Synthesis일반적으로 text-to-speech에서 adversarial feedback 만으로는 generator를 training 하는데 충분하지 않으므로 추가적인 reconstruction loss가 요구됨Multi-SpectroGANGenerator의 self-supervised hidden representation을 conditional discriminator로 conditioning 하여 adversarial feedback만으로 model을 training 함추가적으로 u..
Paper/TTS
2024. 7. 28. 11:12
반응형