The Georgia Tech Center for Music Technology Seminar Series features both invited speakers as well as student project presentations. The seminars are on Mondays from 1:55 - 2:45 p.m. in the West Village Dining Commons, Room 175, on Georgia Tech's campus and are open to the public.
Fall 2022 Seminars
August 22 - Peter Knees - Music Information Retrieval and Recommendation: Recent and Future Development
Abstract: Music information retrieval allows to build new tools for music creation and appreciation based on information in music and how people perceive and interact with it. In this talk, I will present recent research directions in music information retrieval and recommendation at my lab, touching upon various topics such as semantic control of music generation systems, deep learning architectures for music tagging, and reproducibility of user studies in MIR. I will also highlight upcoming projects, such as transformer-based drum pattern generation, sequential music recommendation, and chill factor detection in music to identify common research interests with the faculty at the School of Music.
Peter Knees is an Associate Professor of the Faculty of Informatics, TU Wien, Austria and a Visiting Assistant Professor at Georgia Institute of Technology – School of Music for the fall term 2022. He holds a Master's degree in Computer Science from TU Wien and a PhD in the same field from Johannes Kepler University Linz, Austria. For almost two decades, he has been an active member of the Music Information Retrieval research community, reaching out to the related fields of multimedia and text information retrieval, recommender systems, and the digital arts. His research activities center on music search engines and interfaces as well as music recommender systems, and more recently, on smart(er) tools for music creation. He is one of the proponents of the Digital Humanism initiative of the Faculty of Informatics at TU Wien.
Further information: https://www.ifs.tuwien.ac.at/~knees/
August 29 - Diyi Yang - Building Positive and Responsible Language Technologies
Abstract: Recent advances in natural language processing especially around big models have enabled extensive successful applications. However, there are a growing amount of evidences and concerns towards the negative aspects of NLP systems such as biases and the lack of input from users. How can we build NLP systems that are more aware of human factors and more trustworthy? Our recent work takes a closer look at the social aspect of language via two studies towards building more positive and responsible language technologies. The first one utilizes participatory design to construct a corpus for African American Vernacular English to study dialect disparity, and the second one examines positive reframing by neutralizing a negative point of view and generating a more positive perspective without contradicting the original meaning.
Bio: Diyi Yang is an assistant professor in the School of Interactive Computing at Georgia Tech. She received her PhD from Language Technologies Institute at Carnegie Mellon University in 2019. Her research interests are computational social science and natural language processing. Her research goal is to understand the social aspects of language and to build socially aware NLP systems to better support human-human and human-computer interaction. Her work has received multiple best paper nominations or awards at ACL, ICWSM, EMNLP, SIGCHI, and CSCW. She is a recipient of Forbes 30 under 30 in Science (2020), IEEE “AI 10 to Watch” (2020), the Intel Rising Star Faculty Award (2021), Microsoft Research Faculty Fellowship (2021), and NSF CAREER Award (2022).
September 5 - Labor Day
September 12 - Kahyun ChoiAbstract:
Recently, music complexity has drawn attention from researchers in the field of Music Digital Libraries. In particular, computational methods to measure music complexity have been studied to provide better music services in large-scale music digital libraries. However, the majority of music complexity research has focused on audio-related facets of music, while song lyrics have been rarely considered. Based on the observation that most popular songs contain lyrics, whose different levels of complexity contribute to the overall music complexity, this talk will discuss how to define song lyric complexity and how to measure it computationally. In particular, this talk will focus on the concreteness and the semantic coherence of song lyrics. Finally, the answers to the following questions will be presented: 1) is there an inverted-U relationship between preference and lyric complexity? 2) what is a general trend of lyric complexity? and 3) what is the relationship between lyrics complexity and genres?
Bio: Kahyun Choi is an assistant professor and 2022 Luddy Fellow in the Department of Information and Library Science and Data Science Program at Indiana University Bloomington. She earned her Ph.D. in the School of Information Sciences at the University of Illinois at Urbana-Champaign. Before her Ph.D., she also worked as a software engineer in Naver, a search engine company in Korea. Her research interests include ethical AI workflow for Libraries, Archives, and Museums (LAMs), music information retrieval, public library-based AI education program, computational lyrics analysis, and computational poetry analysis. Her research applies computational methods and machine learning algorithms to audio and text data. She has received awards and fellowships, including the 2021 Institute of Museum and Library Services (IMLS) National Leadership Grant, 2021 Luddy Faculty Fellowship, and 2022 IMLS Early Career Research Development Project Grant.
September 19 - Allie Bashuk
September 26 - Nashlie Sephus
|October 3||Saksham, Shawn, Bowen|
|October 10||Rose, Vedant, Shan|
|October 17||Fall Break|
|October 24||Neha, Xinyu, Ethan|
|October 31||Sile, Michael, Nikhil|
|November 7||Sean, Tilman, Lnhao|
|November 14||Rose, Jocelyn|
|November 21||Noel, Joann, Qinyng|
|November 28||Bryce, Jaui Xu, Kelian, Rosa|
|December 5||Hsing Huang, Nitin, Rhythm, Matthew|