Xi-Peng Qiu

This paper presents Cross-Lingual F5-TTS 2, a simplified framework for transcript-free cross-lingual voice cloning without forced alignment, and makes the syllable-level speaking rate predictor robust to leading and trailing silence through silence-aware augmentation.

Fine-grained cross-modal alignment in audio-video generation can dramatically enhance synchronization and quality, as shown by OmniVAE's innovative training approach.

ABOPD achieves a remarkable 0.42 Å reduction in RMSD for antibody CDR design, setting a new standard for structural fidelity in protein generation.

Cinematic speech data unlocks more realistic and controllable voice generation from natural language descriptions.

Achieve controllable and scalable speech generation with MOSS-TTS, enabling zero-shot voice cloning and long-form synthesis.