殷翔Stephen

Stephen 殷翔 is currently the Ads Foundation ML Lead at ByteDance, where they focus on multi-modal LLM and human video generation. They have two years of professional experience in speech synthesis and a keen interest in speech interaction and related fields. Prior to ByteDance, they held positions as a senior researcher at Tencent and iFLYTEK, specializing in machine learning algorithms and singing synthesis. Stephen completed a Ph.D. in Electronic Engineering and Information Science at the University of Science and Technology of China, where they also earned a bachelor's degree in Electrical, Electronics, and Communications Engineering.