Summary
Wei Xu is a seasoned software engineer with 11+ years building production speech technologies—ASR, TTS, speaker recognition and conversation transcription—across automotive, cloud and real-time communication products. He has driven end-to-end features from algorithm integration to cross-platform SDKs and cloud microservices, shipping work that touched millions of users at Microsoft and Meta. Comfortable turning ambiguous requirements into concrete designs, Wei spans C++/C#, cross-platform mobile/embedded ports, WebRTC and Azure-backed services while mentoring junior engineers and supporting customers. He brings deep hands-on audio expertise from embedded automotive firmware to real-time social media voice at scale, and has a research background in speech recognition and language ID from the Chinese Academy of Sciences.
11 years of coding experience
20 years of employment as a software developer
Master, EE, Master, EE at Chongqing University
Speech Recognition, Language Identification, Speech Recognition, Language Identification at Institute of Acoustics, Chinese Academy of Sciences
Chinese, English