Gus Xia

Assistant Professor of Machine Learning

Research interests

Xia’s research is very interdisciplinary. He is broadly interested in the design of interactive intelligent systems to extend human musical creation and expression. This research lies in the intersection of machine learning, HCI, robotics, and computer music. Some representative works include interactive composition via style transfer, human-computer interactive performances, autonomous dancing robots, large-scale content-based music retrieval, haptic guidance for flute tutoring, and bio-music computing using slime mold.

Email

Xia is a Global Network Assistant Professor in Computer Science at New York University, Shanghai. He also holds affiliations at Tandon, CILVR at the Center for Data Science, and MARL at Steinhardt. He received his Ph.D. in the machine learning department at Carnegie Mellon University (CMU) in 2016, and he was a Neukom Fellow at Dartmouth from 2016 to 2017.

Xia is also a professional Di and Xiao (Chinese flute and vertical flute) player. He plays as a soloist in the NYU Shanghai Jazz ensemble, Pitt Carpathian Ensemble, and Chinese Music Institute of Peking University.

  • Ph.D. in machine learning from Carnegie Mellon University, Pennsylvania, USA
  • Bachelor of Science in information management and information system (minor of psychology) from Peking University, China
  • Private DI (Chinese flute) performance study from the China Conservatory of Music, China
  • Keynote speaker, DMRN+16: Digital Music Research Network One-day Workshop, 2021
  • Keynote speaker, TechMe Week, Online & Tencent, 2021
  • “MIR for Human Health and Potential” panelist, ISMIR, 2021
  • Panel chair on “MIR Technology Across Culture”, ISMIR, 2021
  • General co-chair for NIME Conference, 2021
  • Keynote speaker, Seeds for the Future Year End Celebration, Online, 2020
  • Music co-chair for MuMe workshop, 2019
  • Eastern Young Scholar, Shanghai Ministry of Education, 2017
  • “Future of MIR” panelist, ISMIR, 2017
  • Music chair for ISMIR Conference, 2017
  • Turing Test for Creative Arts Competition Organizer, Dartmouth College, 2017
  • 3-Minute Thesis Presentation Competition Finalist, Carnegie Mellon University, 2015
  • Graduate Student Assembly Representative, Carnegie Mellon University, 2013-2014
  • Team Leader for OurCS Computer Music Group, Carnegie Mellon University, 2013, 2015
  • Outstanding Society Leadership Award (2 out of 260), Peking University, 2009
  • President and Music Director of Chinese Music Institute, Peking University, 2007-2009
  • Volunteer for Olympic Games, Beijing, 2008
  • Selected Student Delegation out of 2000+ candidates for BESETOHA Forum, Tokyo, 2007
  • 1st place out of 3000+ in the National Musical Instrument Proficiency Evaluation, China, 2006

Xia researches and designs intelligent systems to “understand” and “extend” musical creativity and expression. To “understand” means to learn the musical representation conveyed through sounds, performances, and symbolic compositions. To “extend” means to use such an understanding to create artificial music partners, serving music lovers at all levels.

  • Wang, D. Xu, G. Xia, Y. Shan, “Audio-to-symbolic Arrangement via Cross-modal Music Representation Learning”, in Proc. 47th International Conference on Acoustics, Speech and Signal Processing. Singapore & Online, May 2022.
  • Wei, G. Xia, W. Gao, L. Lin, Y. Zhang, “Music Phrase Inpainting Using Long-term Representation and Contrastive Loss”, in Proc. 47th International Conference on Acoustics, Speech and Signal Processing. Singapore & Online, May 2022.
  • Chin, G. Xia, “A Computer-aided Multimodal Music Learning System with Curriculum: A Pilot Study”, in Proc. 2nd International Conference on New Interfaces for Musical Expression, New Zealand, July 2021.
  • Piao, G. Xia, “Sensing the Breath: A Multimodal Singing Tutoring Interface with Breath Guidance”, in Proc. 2nd International Conference on New Interfaces for Musical Expression, New Zealand, July 2021.
  • 2021 Zhao, G. Xia, “AccoMontage: Accompaniment Arrangement via Phrase Selection and Style Transfer”, in Proc. 22nd International Society for Music Information Retrieval Conference, Online, Oct 2021.
  • Lin, Q. Kong, J. Jiang, G. Xia, “A Unified Model for Zero-shot Music Source Separation, Transcription and Synthesis”, in Proc. 22nd International Society for Music Information Retrieval Conference, Online, Oct 2021.

Contact faculty affairs

Interested in working with our renowned faculty?
Fill out the below form and we will get back to you.