Music and Audio Computing Lab

Main menu: Home | People | Research | Publications |

Content-based Music Retrieval

In the recent past, music has become ubiquitous as digital data. The scale of music content in online music and video sharing services has significantly increased and we can readily access to them. This posed challenges in terms of efficient and effective content organization, search and recommendation. In this project, we explore machine learning algorithms, particularly unsupervised feature learning and deep learning, to automatically annotate music in terms of genre, mood, instruments, artist and other music descriptions.

DCNN architecture for music auto-tagging

Multi-Level and Multi-Scale Feature Aggregation Model for Music Auto-Tagging


Related Publications

  • Multi-Level and Multi-Scale Feature Aggregation Using Sample-level Deep Convolutional Neural Networks for Music Classification
    Jongpil Lee and Juhan Nam
    Machine Learning for Music Discovery Workshop, International Conference on Machine Learning (ICML), 2017 [pdf]
  • Sample-level Deep Convolutional Neural Networks for Music Auto-Tagging Using Raw Waveforms
    Jongpil Lee, Jiyoung Park, Keunhyoung Luke Kim and Juhan Nam
    Proceedings of the 14th Sound and Music Computing Conference, 2017 [pdf]
  • Multi-Level and Multi-Scale Feature Aggregation Using Pre-trained Convolutional Neural Networks for Music Auto-Tagging
    Jongpil Lee and Juhan Nam
    IEEE Signal Processing Letters, 2017
  • Sparse Feature Learning for Instrument Identification: Effects of Sampling and Pooling Methods
    Yoonchang Han, Subin Lee, Juhan Nam and Kyogu Lee
    Journal of the Acoustical Society of America (JASA), 2016 [pdf]
  • A Deep Bag-of-Features Model for Music Auto-Tagging
    Juhan Nam, Jorge Herrera, Kyogu Lee
    arXiv preprint arXiv:1508.04999, 2015 [pdf]
  • Learning Sparse Feature Representations for Music Annotation and Retrieval
    Juhan Nam, Jorge Herrera, Malcolm Slaney and Julius O. Smith
    Proceedings of the 13th International Conference for Music Information Retrieval (ISMIR) Conference, 2012 [pdf]

Participants

Keunhyoung Kim, Jongpil Lee, Jiyoung Park and Juhan Nam


Funding

  • NAVER - industry research fund, 2017-2018
  • KAIST - research start-up fund for new faculty, 2014-2017