Meta-TTS: Meta-Learning for Few-Shot Speaker Adaptive Text-to-Speech. (arXiv:2111.04040v3 [cs.SD] UPDATED)

Personalizing a speech synthesis system is a highly desired application,
where the system can generate speech with the user's voice with rare enrolled
recordings. There are two main approaches to build such a system in recent
works: speaker adaptation and speaker encoding. On the one hand, speaker
adaptation methods fine-tune a trained multi-speaker text-to-speech (TTS) model
with few enrolled samples. However, they require at least thousands of
fine-tuning steps for high-quality adaptation, making it hard to apply on
devices. On …

arxiv learning meta meta-learning speech text text-to-speech tts