CrossSpeech++：语言与说话人解耦生成的跨语言语音合成
CrossSpeech++: Cross-lingual Speech Synthesis with Decoupled Language and Speaker Generation
AI总结：
本文提出CrossSpeech++，通过将语音生成拆分为语言相关和说话人相关两个生成器来解耦语言与说话人信息，显著提升跨语言语音合成质量并大幅超越现有方法。
摘要：
本工作的目标是在保持同一说话人身份的同时生成多种语言的自然语音，这一任务被称为跨语言语音合成。跨语言语音合成的一个关键挑战是语言-说话人纠缠问题，该问题导致跨语言系统的质量落后于语言内系统。在本文中，我们提出CrossSpeech++，它有效地解耦语言和说话人信息，并显著提升跨语言语音合成的质量。为此，我们将复杂的语音生成流程拆分为两个简单的组成部分：语言相关生成器和说话人相关生成器。语言相关生成器产生不受特定说话人属性偏置的语言变化。说话人相关生成器对表征说话人身份的声学变化进行建模。通过在不同的模块中处理每种类型的信息，我们的方法能够有效地解耦语言和说话人表示。我们使用多种指标进行了广泛的实验，并证明CrossSpeech++在跨语言语音合成中取得了显著改进，以较大幅度超越了现有方法。
英文摘要：
The goal of this work is to generate natural speech in multiple languages while maintaining the same speaker identity, a task known as cross-lingual speech synthesis. A key challenge of cross-lingual speech synthesis is the language-speaker entanglement problem, which causes the quality of cross-lingual systems to lag behind that of intra-lingual systems. In this paper, we propose CrossSpeech++, which effectively disentangles language and speaker information and significantly improves the quality of cross-lingual speech synthesis. To this end, we break the complex speech generation pipeline into two simple components: language-dependent and speaker-dependent generators. The language-dependent generator produces linguistic variations that are not biased by specific speaker attributes. The speaker-dependent generator models acoustic variations that characterize speaker identity. By handling each type of information in separate modules, our method can effectively disentangle language and speaker representation. We conduct extensive experiments using various metrics, and demonstrate that CrossSpeech++ achieves significant improvements in cross-lingual speech synthesis, outperforming existing methods by a large margin.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
