SuLi
Entering the World of Audio Signals with Python
I am currently an Associate Research Fellow at the Institute of Information Science, Academia Sinica. My research interests span across artificial intelligence, multimedia, and music information retrieval. I have received the Young Scholar Innovation Award from the Foundation for the Advancement of Outstanding Scholarship, the Best Paper Award from the International Society for Music Information Retrieval Conference (ISMIR), and was a finalist for the Best Paper Award at the ACM International Conference on Multimedia (ACM MM). I have been invited to be a speaker at the 29th Golden Melody Awards International Forum and have participated in performances such as "Musical Translations of the Times" (at the National Concert Hall in 2017) and "Whispers of the Night" (at the Weiwuying Performance Hall in Kaohsiung in 2019).
Website: https://homepage.iis.sinica.edu.tw/pages/lisu/index_zh.html
Sound is omnipresent in our daily lives, yet it often remains an overlooked element. In this talk, we will explore the basics of audio processing using Python from a data science perspective. We will discuss the characteristics of time-domain data, important mathematical tools, and artificial intelligence related to audio. Additionally, we will focus on how to use these tools to handle complex musical and biological signals. Finally, we aim to present the multifaceted nature of contemporary music AI research, covering applications from music generation and human-computer interaction in music to the study of musical cultural heritage.
Since most current AI applications focus on text and image processing, I believe there will be significant interest in the applications and principles of audio processing. Through this talk, we hope to introduce what can be achieved with Python in audio processing and music AI, and to share personal insights on using Python as a research tool.