Summary
Yongliang He is a graduate research assistant at Georgia Tech pursuing a joint Master's in Electrical and Computer Engineering and Music Technology, with nine years of hands-on experience in speech and audio research. He focuses on ASR, DSP, TTS, singing voice synthesis, and MIR, and prototypes both deep learning and HMM-based systems for English and Mandarin. His work spans research, teaching (ECE 6250), and industry internships where he integrated prosodic and acoustic cues into NLU and dialog systems to resolve ambiguity and detect sarcasm. Comfortable with toolkits like Kaldi and full-stack prototyping, he brings a rare combination of audio signal intuition and practical system-building for smart devices and voice interfaces. Based in Atlanta, he is actively seeking speech/audio/music tech opportunities and often blends musical insight into technical solutions.
9 years of coding experience
Master's degree, Electrical and Computer Engineering & Music Technology, Master's degree, Electrical and Computer Engineering & Music Technology at Georgia Institute of Technology