Il-Young Jeong

Ph.D. Student

Contacts

finejuly@snu.ac.kr Homepage

Research Interests

  • Blind/informed source separation
  • Statistical modeling for music
  • Deep learning

Publications

  • Singing voice separation using RPCA with weighted l1-norm, I.-Y. Jeong and K. Lee, in Proc. International Conference on Latent Variable Analysis and Signal Separation (LVA/ICA), Grenoble, France, 2017. (submitted)
  • Learning temporal features using a deep neural network and its application to music genre classification, I.-Y. Jeong and K. Lee, in Proc. International Society for Music Information Retrieval Conference (ISMIR), New York, USA, 2016.
  • Informed source separation from monaural music with limited binary time-frequency annotation, I.-Y. Jeong and K. Lee, in Proc. IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Brisbane, Australia, 2015.
  • Vocal separation from monaural music using temporal/spectral continuity and sparsity constraints, I.-Y. Jeong and K. Lee, IEEE Signal Processing Letters, vol. 21, no.10, 1197-1200, Jun. 2014.
  • Singing voice separation based on sparse nature and spectral/temporal discontinuity, I.-Y Jeong and K. Lee, in Music Information Retrieval Evaluation eXchange (MIREX) : singing voice separation, 2014.
  • Vocal separation using extended robust principal component analysis with Schatten p/lp-norm and scale compression, I.-Y. Jeong and K. Lee, in Proc. IEEE International Conference on Machine Learning for Signal Processing (MLSP), Reims, France, Sep. 2014.
  • Single-channel speech dereverberation based on non-negative blind deconvolution and prior imposition on speech and filter, I.-Y. Jeong and B. Kim, and H.-M. Park, in Proc. International Conference on Neural Information Processing (ICONIP), pp. 45-46, Nov. 2013.
  • 반복적 마스킹을 이용한 NMF 기반 비지도 드럼 채보 (Unsupervised drum transcription using iteratively masked non-negative matrix factorization), I.-Y. Jeong and K. Lee, in Proc. 신호처리학술대회 (Korea Signal Processing Conference), 2013. (Korean, Best paper)
  • 스펙트로그램의 정규화 경사와 비음수 행렬 분해에 기반한 음악 잡음 제거 알고리즘 (Music noise reduction based on the normalized gradient on spectrogram and non-negative matrix factorization), I.-Y. Jeong and H.-M. Park, in Proc. 한국음성학회 (Conference of the Korean Society of Speech Sciences), 2013. (Korean)
  • 정일영, “음성과 반향 필터의 사전정보를 이용한 비음수 행렬 분해 기반 음성 반향 제거,” 석사학위논문, 서강대학교, 2012.
  • 박형민,정일영, “사운드 신호를 기반으로 한 반주제공방법 및 이를 이용한 반주제공장치,” 대한민국 등록년 2014년, 등록번호 10-1361033.
  • 박형민,정일영, “단일채널 음성신호에 대한 반향신호 제거방법 및 이를 이용한 음성인식장치, ” 대한민국 등록년 2013년, 등록번호 10-1334991.

Projects

  • Automatic Music Accompaniment
  • Music-lyrics Alignment
  • Blind Source Separation