Experience

As a co-founder, I work to bring speech technology to more languages and markets and apply it in real-world scenarios such as video translation and comic-drama dubbing. My work spans product direction, multilingual data and model pipelines, speech quality evaluation, prototype iteration, and delivery feedback loops, turning low-resource TTS and intelligent dubbing research into reliable product capabilities. Company website: luoji.cn.

Worked in the Foundation Model team on Instruct TTS based on CosyVoice and LLASA, and on continuous-feature-based speech synthesis and controllable singing voice synthesis based on VibeVoice and Ming-Omni-TTS for in-car voice interaction. The work covered data construction, model training, evaluation, and product-oriented validation for controllable, high-quality speech generation.