CrossSpeech: Speaker-independent Acoustic Representation for Cross-lingual Speech Synthesis

arxiv(2023)

引用 3|浏览2
暂无评分
摘要
While recent text-to-speech (TTS) systems have made remarkable strides toward human-level quality, the performance of cross-lingual TTS lags behind that of intra-lingual TTS. This gap is mainly rooted from the speaker-language entanglement problem in cross-lingual TTS. In this paper, we propose CrossSpeech which improves the quality of cross-lingual speech by effectively disentangling speaker and language information in the level of acoustic feature space. Specifically, CrossSpeech decomposes the speech generation pipeline into the speaker-independent generator (SIG) and speaker-dependent generator (SDG). The SIG produces the speaker-independent acoustic representation which is not biased to specific speaker distributions. On the other hand, the SDG models speaker-dependent speech variation that characterizes speaker attributes. By handling each information separately, CrossSpeech can obtain disentangled speaker and language representations. From the experiments, we verify that CrossSpeech achieves significant improvements in cross-lingual TTS, especially in terms of speaker similarity to the target speaker.
更多
查看译文
关键词
synthesis,crossspeech,speaker-independent,cross-lingual
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