I’m currently a second-year Master’s student in the Language Technologies Institute at CMU, working with Prof.Carolyn Penstein Rose. Lately, I finished my Siri TTS R&D summer internship just now.
During my undergraduate studies at National Taiwan University, my research spanned areas in computational linguistics, signal processing, and computer vision, under the supervision of Prof. Lin-shan Lee, Prof. Hung-yi Lee, and Prof. Yu-chiang Frank Wang.
I was also a Natural Language Processing Intern in DeepHow, the first AI company bridging the skills gap in manufacturing, service and repair through an AI-powered knowledge capturing and training platform based on smart how-to videos. I was responsible for the AI algorithm development, which has been deployed to more than 40 Siemens service centers worldwide.
MS in Intelligent Information Systems, 2021
Carnegie Mellon University
BS in Electrical Engineering, 2020
National Taiwan University
Disentanglement for 3D Point Cloud | Demo | Report
Conventional Computer Vision | Demo
Speech Disentanglement and Voice Conversion
Personalized Dialogue Generation | Demo | Paper
Large-vocabulary Speech Recognition System
Understood the needs of the modeling teams and created robust scripts and systems that meet the needs.
Developed a robust system that detects anomaly in data and reduces considerably the required evaluation time.
Unsupervised Temporal Embedding for video segmentation
Researched on self-supervised multi-modal networks and helped develop video recommendation systems.
Implemented an unsupervised architecture, detected and segmented actions in untrimmed videos, and deployed on the DeepHow platform - AI Stephanie, improving the accuracy by 30%.
Step-embedding for video recommendation
Developed a brand-new sentence embedding method by encoding ASR sentences from video clips.
Verified on real-world videos, the generated embedding contains features from the texts and recommend other video clips.
Software Engineering Intern
Generative Model for Image Morphing