IDEAS home Printed from https://ideas.repec.org/a/gam/jmathe/v9y2021i5p530-d509902.html
   My bibliography  Save this article

DBTMPE: Deep Bidirectional Transformers-Based Masked Predictive Encoder Approach for Music Genre Classification

Author

Listed:
  • Lvyang Qiu

    (Department of Multimedia Engineering, Dongguk University–Seoul, Seoul 04620, Korea)

  • Shuyu Li

    (Department of Multimedia Engineering, Dongguk University–Seoul, Seoul 04620, Korea)

  • Yunsick Sung

    (Department of Multimedia Engineering, Dongguk University–Seoul, Seoul 04620, Korea)

Abstract

Music is a type of time-series data. As the size of the data increases, it is a challenge to build robust music genre classification systems from massive amounts of music data. Robust systems require large amounts of labeled music data, which necessitates time- and labor-intensive data-labeling efforts and expert knowledge. This paper proposes a musical instrument digital interface (MIDI) preprocessing method, Pitch to Vector (Pitch2vec), and a deep bidirectional transformers-based masked predictive encoder (MPE) method for music genre classification. The MIDI files are considered as input. MIDI files are converted to the vector sequence by Pitch2vec before being input into the MPE. By unsupervised learning, the MPE based on deep bidirectional transformers is designed to extract bidirectional representations automatically, which are musicological insight. In contrast to other deep-learning models, such as recurrent neural network (RNN)-based models, the MPE method enables parallelization over time-steps, leading to faster training. To evaluate the performance of the proposed method, experiments were conducted on the Lakh MIDI music dataset. During MPE training, approximately 400,000 MIDI segments were utilized for the MPE, for which the recovery accuracy rate reached 97%. In the music genre classification task, the accuracy rate and other indicators of the proposed method were more than 94%. The experimental results indicate that the proposed method improves classification performance compared with state-of-the-art models.

Suggested Citation

  • Lvyang Qiu & Shuyu Li & Yunsick Sung, 2021. "DBTMPE: Deep Bidirectional Transformers-Based Masked Predictive Encoder Approach for Music Genre Classification," Mathematics, MDPI, vol. 9(5), pages 1-17, March.
  • Handle: RePEc:gam:jmathe:v:9:y:2021:i:5:p:530-:d:509902
    as

    Download full text from publisher

    File URL: https://www.mdpi.com/2227-7390/9/5/530/pdf
    Download Restriction: no

    File URL: https://www.mdpi.com/2227-7390/9/5/530/
    Download Restriction: no
    ---><---

    References listed on IDEAS

    as
    1. Shuyu Li & Sejun Jang & Yunsick Sung, 2019. "Automatic Melody Composition Using Enhanced GAN," Mathematics, MDPI, vol. 7(10), pages 1-13, September.
    Full references (including those not matched with items on IDEAS)

    Citations

    Citations are extracted by the CitEc Project, subscribe to its RSS feed for this item.
    as


    Cited by:

    1. Shuyu Li & Yunsick Sung, 2023. "MRBERT: Pre-Training of Melody and Rhythm for Automatic Music Generation," Mathematics, MDPI, vol. 11(4), pages 1-14, February.
    2. Yihang Zhang & Yunsick Sung, 2023. "Traffic Accident Detection Using Background Subtraction and CNN Encoder–Transformer Decoder in Video Frames," Mathematics, MDPI, vol. 11(13), pages 1-15, June.
    3. Yu-Huei Cheng & Che-Nan Kuo, 2022. "Machine Learning for Music Genre Classification Using Visual Mel Spectrum," Mathematics, MDPI, vol. 10(23), pages 1-19, November.
    4. Zhe Jiang & Shuyu Li & Yunsick Sung, 2022. "Enhanced Evaluation Method of Musical Instrument Digital Interface Data based on Random Masking and Seq2Seq Model," Mathematics, MDPI, vol. 10(15), pages 1-17, August.
    5. Yihang Zhang & Yunsick Sung, 2023. "Traffic Accident Detection Method Using Trajectory Tracking and Influence Maps," Mathematics, MDPI, vol. 11(7), pages 1-14, April.

    Most related items

    These are the items that most often cite the same works as this one and are cited by the same works as this one.
    1. Shuyu Li & Yunsick Sung, 2023. "Transformer-Based Seq2Seq Model for Chord Progression Generation," Mathematics, MDPI, vol. 11(5), pages 1-14, February.
    2. Arulsamy, Karen & Delaney, Liam, 2022. "The impact of automatic enrolment on the mental health gap in pension participation: Evidence from the UK," Journal of Health Economics, Elsevier, vol. 86(C).
    3. Wenkai Huang & Feng Zhan, 2023. "A Novel Probabilistic Diffusion Model Based on the Weak Selection Mimicry Theory for the Generation of Hypnotic Songs," Mathematics, MDPI, vol. 11(15), pages 1-26, July.
    4. Shuyu Li & Yunsick Sung, 2021. "INCO-GAN: Variable-Length Music Generation Method Based on Inception Model-Based Conditional GAN," Mathematics, MDPI, vol. 9(4), pages 1-16, February.
    5. Shuyu Li & Yunsick Sung, 2023. "MRBERT: Pre-Training of Melody and Rhythm for Automatic Music Generation," Mathematics, MDPI, vol. 11(4), pages 1-14, February.
    6. Sejun Jang & Shuyu Li & Yunsick Sung, 2020. "FastText-Based Local Feature Visualization Algorithm for Merged Image-Based Malware Classification Framework for Cyber Security and Cyber Defense," Mathematics, MDPI, vol. 8(3), pages 1-13, March.
    7. Hyewon Yoon & Shuyu Li & Yunsick Sung, 2021. "Style Transformation Method of Stage Background Images by Emotion Words of Lyrics," Mathematics, MDPI, vol. 9(15), pages 1-20, August.

    Corrections

    All material on this site has been provided by the respective publishers and authors. You can help correct errors and omissions. When requesting a correction, please mention this item's handle: RePEc:gam:jmathe:v:9:y:2021:i:5:p:530-:d:509902. See general information about how to correct material in RePEc.

    If you have authored this item and are not yet registered with RePEc, we encourage you to do it here. This allows to link your profile to this item. It also allows you to accept potential citations to this item that we are uncertain about.

    If CitEc recognized a bibliographic reference but did not link an item in RePEc to it, you can help with this form .

    If you know of missing items citing this one, you can help us creating those links by adding the relevant references in the same way as above, for each refering item. If you are a registered author of this item, you may also want to check the "citations" tab in your RePEc Author Service profile, as there may be some citations waiting for confirmation.

    For technical questions regarding this item, or to correct its authors, title, abstract, bibliographic or download information, contact: MDPI Indexing Manager (email available below). General contact details of provider: https://www.mdpi.com .

    Please note that corrections may take a couple of weeks to filter through the various RePEc services.

    IDEAS is a RePEc service. RePEc uses bibliographic data supplied by the respective publishers.