Xingyu Na is a Senior Speech R&D Engineer with 13 years of experience specializing in speech signal processing, ASR, TTS, and acoustic encoding, and over three years focused on deep learning. Currently at Apple after senior roles at Microsoft and leadership of Alibaba Robotics’ speech and dialog team, he designs and delivers production acoustic models and lightweight on-device voice interaction systems. He is a heavy Kaldi and HTS user and contributor, and his open-source work includes DevOps improvements to the widely used Espnet toolkit, improving CI/CD reliability for end-to-end speech processing. His background blends academic rigour—a PhD in Speech Technology—with hands-on engineering across cloud ASR services and embedded noise suppression. Notably, he began in missile automation guidance before pivoting to speech, giving him a rare combination of systems thinking and signal-processing depth.
13 years of coding experience
11 years of employment as a software developer
Bachelor's Degree, Missile Automation Guidance, Bachelor's Degree, Missile Automation Guidance at Beijing Institute of Technology
Contributions:5 commits, 3 PRs, 3 comments in 19 days
Contributions summary:Xingyu primarily focused on improving the build and CI/CD pipeline of the project. Their contributions included fixing CI failures, ensuring the correct handling of paths in the build scripts, and resolving errors in the installation process. Additionally, the user addressed a typo in a download script related to data preparation. This suggests a focus on improving the reliability and usability of the project's build and deployment infrastructure.
Contributions:16 commits, 12 pushes, 1 branch in 1 month
Find and Hire Top DevelopersWe’ve analyzed the programming source code of over 60 million software developers on GitHub and scored them by 50,000 skills. Sign-up on Prog,AI to search for software developers.