BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Memento EPFL//
BEGIN:VEVENT
SUMMARY:AI Center X LSI Lab Seminar - Artificial Intelligence for Musician
 s
DTSTART:20250318T150000
DTEND:20250318T160000
DTSTAMP:20260430T115154Z
UID:0bd8c358b86ef2abb4236c471943129e7ef5bf8e7808b479a18751fb
CATEGORIES:Conferences - Seminars
DESCRIPTION:Kristen Yeon-Ji Yun and Yung-Hsiang Lu\nThe talk is jointly or
 ganized by the LSI Lab and the EPFL AI Center.\n\nFor on-site logistic
 s\, please use the following form to register (with your EPFL email addre
 ss): Here. \nThe talk will be followed by a coffee session.\n\nHost: Pro
 f. Giovanni De Micheli\n\nTitle\nArtificial Intelligence for Musicians\n\n
 Abstract\nThis seminar will introduce how AI-embedded tools can be benefic
 ial to improve individual practice and performance for string professional
 s and students\, offering insights from a professional musician. The requi
 site technologies for this integration encompass score digitization and pr
 ocessing\, audio input measurement and comparison to score\, dynamic estim
 ation\, and tempo/downbeat estimation\, posture detection for hands and bo
 dy\, and bow/instruments detection. The purpose of technological developme
 nt is to solve those two research questions. (1) When can AI technology pr
 ovide measurable benefits to professional musicians' practice and performa
 nce? (2) What factors would affect future musicians' acceptance of AI tech
 nology in their work?\n \nWe will also present the new technology we are 
 developing in musical error detection in practice. The current available t
 echnology has two major limitations: (1) They rely on automatic alignment 
 and (2) They rely on heuristics due to the lack of training data. We devel
 op a new method using machine learning based on transformers that accept a
 udio synthesized as music scores as a reference\, and the recorded music l
 earners' performance. This neural architecture can be trained end-to-end a
 nd eliminates the need for explicit alignment. We also synthesize a large 
 dataset for training and evaluation. This method can be applied to multipl
 e instruments and improves detection F1 score by as much as 41 percent.\n\
 nBio\nKristen Yeon-Ji Yun is a clinical associate professor in the Departm
 ent of Music in the Patti and Rusty Rueff School of Design\, Art\, and Per
 formance at Purdue University. She is active as a soloist\, chamber musici
 an\, musical scholar\, and clinician. Her CD “Summerland” has excellen
 t 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 in
 ternationally. Her dynamic career includes receiving a grant as a principa
 l investigator from the National Science Foundation for the project "Artif
 icial Intelligence Technology for Future MusicPerformers." Her research te
 am is exploring various applications of AI in music\, including Automatic 
 Music Transcription\, the Robot Cello\, and MUS2VID. She received the Doct
 or of Music on cello performance in 2012 from Indiana University Jacobs Sc
 hool of Music at Bloomington\, where she studied with the world-famous cel
 list Janos Starker. She received master and bachelor degrees in cello perf
 ormance from Seoul National University.\n\nYung-Hsiang Lu is a professor o
 f Electrical and Computer Engineering at Purdue University. He is a Univer
 sity Faculty Scholar of Purdue University. He is a fellow of the IEEE (Ins
 titute 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 co
 mpetitions\; 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 “I
 ntermediate C Programming" (2nd ISBN 978-1-0321-8981-9\, 1st ISBN 978-1-49
 87-1163-0)\, “Low-Power Computer Vision Improve the Efficiency of Artifi
 cial Intelligence” (ISBN 978-0-3677-4470-0). He received Ph.D. from Stan
 ford University\, BSEE from National Taiwan University.\n 
LOCATION:ELE 117 https://plan.epfl.ch/?room==ELE%20117 https://epfl.zoom.u
 s/j/69425366580?pwd=tTIT3kzXzajohOhMcgv8CGMeMBYbnl.1
STATUS:CONFIRMED
END:VEVENT
END:VCALENDAR