AI Center X LSI Lab - Artificial Intelligence for Musicians - Profs. Yeon-Ji Yun & Yung-Hsiang скачать в хорошем качестве

AI Center X LSI Lab - Artificial Intelligence for Musicians - Profs. Yeon-Ji Yun & Yung-Hsiang

The talk was jointly organized by the Integrated Systems Laboratory Lab and the EPFL AI Center. Title Artificial Intelligence for Musicians Abstract This seminar will introduce how AI-embedded tools can be beneficial to improve individual practice and performance for string professionals and students, offering insights from a professional musician. The requisite technologies for this integration encompass score digitization and processing, audio input measurement and comparison to score, dynamic estimation, and tempo/downbeat estimation, posture detection for hands and body, and bow/instruments detection. The purpose of technological development is to solve those two research questions. (1) When can AI technology provide measurable benefits to professional musicians' practice and performance? (2) What factors would affect future musicians' acceptance of AI technology in their work? We will also present the new technology we are developing in musical error detection in practice. The current available technology has two major limitations: (1) They rely on automatic alignment and (2) They rely on heuristics due to the lack of training data. We develop a new method using machine learning based on transformers that accept audio synthesized as music scores as a reference, and the recorded music learners' performance. This neural architecture can be trained end-to-end and eliminates the need for explicit alignment. We also synthesize a large dataset for training and evaluation. This method can be applied to multiple instruments and improves detection F1 score by as much as 41 percent. Bio Kristen Yeon-Ji Yun is a clinical associate professor in the Department of Music in the Patti and Rusty Rueff School of Design, Art, and Performance at Purdue University. She is active as a soloist, chamber musician, musical scholar, and clinician. Her CD “Summerland” has excellent reviews from New Classics UK, American Record Guide, and was broadcast nationwide. Dr. Yun is a winner in numerous competitions around the world and has been giving a series of successful concerts and master classes internationally. Her dynamic career includes receiving a grant as a principal investigator from the National Science Foundation for the project "Artificial Intelligence Technology for Future MusicPerformers." Her research team is exploring various applications of AI in music, including Automatic Music Transcription, the Robot Cello, and MUS2VID. She received the Doctor of Music on cello performance in 2012 from Indiana University Jacobs School of Music at Bloomington, where she studied with the world-famous cellist Janos Starker. She received master and bachelor degrees in cello performance from Seoul National University. Yung-Hsiang Lu is a professor of Electrical and Computer Engineering at Purdue University. He is a University Faculty Scholar of Purdue University. He is a fellow of the IEEE (Institute of Electrical and Electronics Engineers), distinguished visitor of the Computer Society, distinguished scientist and distinguished speaker of the ACM (Association for Computing Machinery). Dr. Lu is the inaugural director of Purdue’s John Martinson Engineering Entrepreneurial Center (2020-2022). He has advised multiple student teams winning business plan competitions; two teams of students started technology companies and raised more than $1.5M. He is the lead organizer of the IEEE Low-Power Computer Vision Challenge since 2015. He is an author or editor of three books “Intermediate C Programming" (2nd ISBN 978-1-0321-8981-9, 1st ISBN 978-1-4987-1163-0), “Low-Power Computer Vision Improve the Efficiency of Artificial Intelligence” (ISBN 978-0-3677-4470-0). He received Ph.D. from Stanford University, BSEE from National Taiwan University. Recording date: March 18, 2025 Location: EPFL Campus, AI Center