Abstract

Research papers usually tell us what worked, what was discovered, and what the results mean. But what about everything that happened along the way? My PhD research, Music Information Analysis using Deep Neural Networks, explored how deep learning can be used to analyze music. Like any research journey, it involved more than models, experiments, and final results. In this talk, I will share some stories from behind my research, including unexpected challenges, surprising discoveries, and experiences that rarely make it into a paper. Along the way, I will share a few things I learned, some things that surprised me, and some thoughts on what doing research is like beyond the final results.

Bio.

Pei-Chun Chang is an AI Engineer at Novatek Microelectronics Corp., specializing in speech separation and audio machine learning for edge devices. She received her B.S. and M.S. degrees in Computer Science from Chung Hua University in 2015 and 2017, respectively, and her Ph.D. in Computer Science from National Yang Ming Chiao Tung University in 2024. Her research interests include audio and speech processing, music information retrieval, and deep learning. Her honors include the Doctoral Excellent Paper Award at the 18th Taiwan Management Association Thesis Awards, the Excellent Paper Award at IIHMSP 2024, and membership in the Phi Tau Phi Scholastic Honor Society.

All faculty and students are welcome to join.