Music and Audio Computing Lab

Main menu: Home | People | Research | Publications |


all together

Our research focuses on exploring computational methods to analyze or synthesize sounds with applications to various musical contexts including music listening, performance, composition, production, education and entertainment. We are particularly interested in developing "musically intelligent machines" that understand sounds, represent the meanings in a human-friendly manner, and generate new musical content.

Recent News

  • [Mar-25-2019] Sangeun's journal paper, "Joint Detection and Classification of Singing Voice Melody Using Convolutional Recurrent Neural Networks" has been accepted for Applied Sciences.
  • [Mar-19-2019] Taejun's journal paper, "Comparison and Analysis of SampleCNN Architectures for Audio Classification" has been accepted for the IEEE Journal of Selected Topics in Signal Processing (J-STSP) (impact factor: 4.36).
  • [Feb-22-2019] We organize "KAISTxSNU Music and Audio Workshop" at KAIST [link].
  • [Jan-22-2019] Prof. Juhan Nam presents a special talk on "Music Performance Machine" in the 14th Korea Robotics Society of Annaul Conference [link].
  • [Jan-1-2019] Our lab research is introduced in the KBS Daejeon TV program, "Homo Science". You can watch it at this [link] .
  • [Oct-20-2018] Prof. Juhan Nam presents "AI Pianist" performance in a Kids Music Event of the annual Daejeon Science Festival [link].
  • [Sep-21-2018] Our journal paper, "Deep Learning for Audio-based Music Classification and Tagging" has been accepted for the IEEE Signal Processing Magazine, Special Issue on Music Signal Processing (impact factor: 7.45). This work was done by collaboration with Keunwoo Choi from Spotify (U.S) and Yi-Hsuan Yang from Acamedia Sinica (Taiwan).
  • [Aug-20-2018] Our paper, "Representation Learning of Music Using Artist Labels" (collaboration research with NAVER), is introduced in the Korean newspaper, Electronic Times (전자신문) [link].
  • [Aug-14-2018] Our "AI Pianist" research was introduced in the Korean news article on the Samsung Research Funding [link].
  • [Aug-13-2018] We invite Prof. Tae Hong Park (NYU) to our lab. He gives a talk on "M^3: Music | Media | Machine".
  • [Jun-25-2018] Prof. Juhan Nam serves as a guest editor for the special issue of the IEEE Journal of Selected Topics in Signal Processing (J-STSP): "Special Issue on Data Science: Machine Learning for Audio Signal Processing" [link].
  • [May-25-2018] Three papers have been accepted in ISMIR2018!
  • [May-17-2018] We invite Dr. Masataka Goto (AIST, Japan) to the SymCT program of CTScape2018. He gives a talk on "Intelligent Music Interface".
  • [Feb-12-2018] We invite Prof. Vesa Välimäki (Aalto University) to our lab. He gives a talk on "Artificial Reverberation and Audio Equalization".
  • [Jan-30-2018] Two papers have been accepted in ICASSP2018.
  • [Jan-17-2018] Jongpil's journal paper, "SampleCNN: End-to-End Deep Convolutional Neural Networks Using Very Small Filters for Music Classification" has been accepted in the special issue "Sound and Music Computing" of Applied Sciences.
  • [Oct-01-2017] We receive a 3-year grant from the Samsung Research Funding for our project titled "Synthesis of Emotionally Expressive Music Performance Using Machine Learning". We will collaboarate with Jonghwa Park, renown concert pianist and professor at SNU [link].
  • [Aug-22-2017] The NeuroScape project by Seungsoon and Jongpil is exhibited in GAS 2017, A.I & Articial Creativity.
  • [Jul-01-2017] We start an industry research project with NAVER on the topic of content-based music recommendation.