Rui Wang
博士研究生 at 同济大学
Jiading District, Shanghai, China
Summary
🤩
Rockstar🎓
Top SchoolRui Wang is a PhD student at Tongji University with a decade of experience researching speech and speaker recognition, combining deep learning, neural architecture search, and pretraining for unified speech-text models. His work includes SpeechT5 (ACL 2022) and Lightweight HuBERT variants, achieving substantial compression and cross-task gains across ASR, TTS, VC, SE, SID and SUPERB benchmarks. He has contributed efficient architecture-search methods for speaker and point-cloud tasks (TASLP, AutoML workshop) and designed a Multi-View Self-Attention transformer that improved VoxCeleb performance (ICASSP). Rui blends rigorous academic publication record with hands-on system-level optimization, and spent a research internship at Microsoft Research Asia translating pretraining ideas into multi-task speech pipelines. A mechanical engineering undergrad turned speech-ML researcher, he brings an uncommon mix of hardware-aware efficiency thinking to large-scale pretraining.
10 years of coding experience
工学硕士, 测试计量技术与仪器, -, 工学硕士, 测试计量技术与仪器, - at 浙江理工大学博士, 计算机科学与技术, 博士, 计算机科学与技术 at 同济大学
Github Skills (49)
representation-learning10
encoder10
chainer10
apc10
text-to-speech10
speech-synthesis10
encoder-decoder10
speech10
spoken-language10
decoder10
speech-processing9
artificial-intelligence9
speaker-diarization9
machine-translation9
pytorch9
Programming languages (1)
Github contributions (5)
mechanicalsea/lighthubert
Mar 2022 - Sep 2022
Contributions:15 commits, 9 pushes, 5 comments in 6 months
mechanicalsea/kaggle-101-Titanic
Mar 2016 - Sep 2017
Contributions:9 commits, 8 pushes, 1 branch in 1 year 6 months
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.