Comparative Analysis of Flow-Matching and Diffusion-Based TTS for Cross-Lingual Voice Cloning in Low-Resource Unseen Languages

Flow-matching-based text-to-speech (TTS) models have shown high-quality speech synthesis. However, most current flow-matching-based TTS models still rely on reference transcripts corresponding to the audio prompt for synthesis. This dependency prevents cross-lingual voice cloning when audio prompt transcripts are unavailable, particularly for unseen languages. The key challenges for flow-matching-based TTS models to remove audio prompt transcripts are identifying word boundaries during training and determining appropriate duration during inference. In this paper, we introduce Cross-Lingual F5-

Research goal: How does the cross-lingual voice cloning performance of flow-matching TTS models compare to diffusion-based TTS models when evaluated on unseen languages with limited training data?

Autonomous synthesis report generated by Assignee Research. Tribunal consensus score: 9.2/10.