Chih-Pin Tan (譚至斌)

Ph.D. student @ National Taiwan University and Research scientist @ KKCompany.

prof_pic.jpg

Music is so fascinating

I am a Ph.D. student, advised by Yi-Hsuan Yang, in the Graduate Institute of Communication Engineering at National Taiwan University, and also a research scientist at KKCompany. My research interests are Musc Information Retrieval/Research (MIR) related topics, including music generation, music analysis, and deep learning applications on music. I am particularly interested in cover song generation and symbolic music generation. My goal is to develope algorithms that can understand music and help musician to creating wonderful pieces. I am also interested in drawing these research ideas to real-world applications. For example, PiCoGen is a cover song generation system that is completely open-sourced and availible for everyone to use.

selected publications

  1. ICMR
    PiCoGen: Generate Piano Covers with a Two-stage Approach
    Chih-Pin Tan, Shuen-Huei Guan, and Yi-Hsuan Yang
    In Proceedings of the 2024 International Conference on Multimedia Retrieval, 2024
  2. ISMIR
    Melody Infilling with User-Provided Structural Context
    Chih-Pin Tan, Alvin W. Y. Su, and Yi-Hsuan Yang
    In Proc. International Society for Music Information Retrieval, 2022