Xiaobin Rong

Achieve state-of-the-art universal speech enhancement with UniPASE, a model that minimizes linguistic hallucinations by converting degraded waveforms into clean phonetic representations.

Generative and predictive models can be fused to achieve state-of-the-art speech enhancement, outperforming single-branch approaches in robustness and perceptual quality.

Studio-quality speech enhancement without hallucination is now possible, thanks to a clever combination of dry-target finetuning and flow-matching.