Voice Conversion by Cascading Automatic Speech Recognition and Text-to-Speech Synthesis with Prosody

會議：2020 interspeech 作者：zhangjingxuan 單位：科大訊飛&中科大 文章目錄 abstract introduction 2. background 3. proposed method 3.1 ASR engine 3.2 TTS model 3.3. Prosody transfer 4. Experiments 4.1. Experiment condition

>>阅读原文<<