Ming Tu

Ming Tu is a highly skilled tech lead and research scientist specializing in speech and audio foundation models, with a focus on large language model-based speech understanding and generation at ByteDance since April 2020. Prior to this role, Ming served as a research scientist at JD.COM, contributing to speech processing and natural language understanding, and gained valuable experience as a graduate research assistant at Arizona State University. Ming's expertise is further highlighted through internships at Alibaba Group, LG Electronics, the Institute of Acoustics (Chinese Academy of Sciences), Sony China Research Lab, and China Mobile. Ming holds a Ph.D. in Speech and Hearing Science from Arizona State University and a Master’s Degree in Information and Communication Engineering from Beijing Institute of Technology.