Towards Spontaneous Style Modeling with Semi-supervised Pre-training for Conversational Text-to-Speech Synthesis

CoRR(2023)

引用 0|浏览19
暂无评分
摘要
The spontaneous behavior that often occurs in conversations makes speech more human-like compared to reading-style. However, synthesizing spontaneous-style speech is challenging due to the lack of high-quality spontaneous datasets and the high cost of labeling spontaneous behavior. In this paper, we propose a semi-supervised pre-training method to increase the amount of spontaneous-style speech and spontaneous behavioral labels. In the process of semi-supervised learning, both text and speech information are considered for detecting spontaneous behaviors labels in speech. Moreover, a linguistic-aware encoder is used to model the relationship between each sentence in the conversation. Experimental results indicate that our proposed method achieves superior expressive speech synthesis performance with the ability to model spontaneous behavior in spontaneous-style speech and predict reasonable spontaneous behavior from text.
更多
查看译文
关键词
spontaneous style modeling,synthesis,semi-supervised,pre-training,text-to-speech
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要