Cross-Speaker Emotion Transfer for Low-Resource Text-to-Speech Using Non-Parallel Voice Conversion with Pitch-Shift Data Augmentation

Conference of the International Speech Communication Association (INTERSPEECH)(2022)

引用 2|浏览6
暂无评分
摘要
Data augmentation via voice conversion (VC) has been successfully applied to low-resource expressive text-to-speech (TTS) when only neutral data for the target speaker are available. Although the quality of VC is crucial for this approach, it is challenging to learn a stable VC model because the amount of data is limited in low-resource scenarios, and highly expressive speech has large acoustic variety. To address this issue, we propose a novel data augmentation method that combines pitch-shifting and VC techniques. Because pitch-shift data augmentation enables the coverage of a variety of pitch dynamics, it greatly stabilizes training for both VC and TTS models, even when only 1,000 utterances of the target speaker's neutral data are available. Subjective test results showed that a FastSpeech 2-based emotional TTS system with the proposed method improved naturalness and emotional similarity compared with conventional methods.
更多
查看译文
关键词
voice,data augmentation,conversion,cross-speaker,low-resource,text-to-speech,non-parallel,pitch-shift
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