Apr, 2024
HyperTTS: 基于超网络的文本转语音中的参数高效适应
HyperTTS: Parameter Efficient Adaptation in Text to Speech using Hypernetworks
Yingting Li, Rishabh Bhardwaj, Ambuj Mehrish, Bo Cheng, Soujanya Poria
TL;DRNeural speech synthesis and domain adaptation in text-to-speech (TTS) achieved state-of-the-art performance using HyperTTS, a parameter-efficient model with Adapter blocks conditioned on speaker representations through a dynamic hypernetwork.