CrossSpeech++: Cross-lingual Speech Synthesis with Decoupled Language and Speaker Generation

TL;DR

CrossSpeech++ introduces a novel approach to cross-lingual speech synthesis by disentangling language and speaker information, leading to significant quality improvements over existing methods.

Contribution

The paper proposes a decoupled generation framework that separates language and speaker modeling, enhancing cross-lingual speech synthesis quality.

Findings

Outperforms existing methods by a large margin

Effectively disentangles language and speaker representations

Significantly improves cross-lingual speech synthesis quality

Abstract

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.