Music and Audio Computing Lab

Main menu: Home | People | Research | Publications |

Singing Voice Analysis in Polyphonic Music

In popular music, singing voice is the central sound source that determines the song quality, as it conveys melody, lyrics, emotion and humanity with its high expressivity. In this project, we investigate algorithms to analyze various characteristics of vocal sounds from low-level acoustic features (e.g. pitch and timbre) to high-level word descriptions of voice. In particular, we focus on extracting the information in polyphonic settings.

all together

Related Publications

  • Visualization of Singing Expression Using Vibrato Lissajous Figures
    Tae Hyoung Kim and Juhan Nam
    Proceedings of the HCI Korea, 2017
  • Melody Extraction on Vocal Segments Using Multi-Column Deep Neural Networks
    Sangeun Kum, Changheun Oh and Juhan Nam
    Proceedings of International Society for Music Information Retrieval Conference (ISMIR), 2016 [pdf] [website]
  • Investigation on Vocal Tags and Singer Similarity of K-pop
    Jongpil Lee, Tae Hyoung Kim, Sangeun Kum, Keunhyoung Luke Kim, Changheun Oh and Juhan Nam
    Proceedings of the Acoustical Society of Korea Spring Conference, 2016


Sangeun Kum, Changheun Oh, Keunhyoung Kim, Jongpil Lee, Taehyoung Kim, Saebyul Park, Jiyoung Park and Juhan Nam


National Research Foundation of Korea, 2015-2018