RobustSpeechFlow: Learning Robust Text-to-Speech Trajectories via Augmentation-based Contrastive Flow Matching

arXiv:2605. 22083v2 Announce Type: replace-cross Abstract: While flow-matching text-to-speech (TTS) achieves strong zero-shot speaker similarity and naturalness, it remains susceptible to content fidelity issues, particularly skip and repeat errors from imperfect alignment.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

• diffusion
• multimodal
• benchmarks
• safety