Our team won the Best Paper award at the ACM Multimedia Conference 2020 with the paper entitled "PiRhDy: Learning Pitch-, Rhythm-, and Dynamics-aware Embeddings for Symbolic Music". The research team comprised of Hongru Liang, Wenqiang Lei, Prof Maosong Sun, Prof Tat-Seng Chua, as well as two external collaborators, Paul Yaozhu Chan (I²R) and Prof Zhenglu Yang (Nankai University Computer Science).
In their paper, the team presents a novel comprehensive model that forms the basis for a wide range of music tasks, such as music retrieval, genre classification, phrase completion, accomplishment assignment, and music generation. This model can be pre-trained on large-scale music datasets, and easily fine-tuned for different tasks. It successfully demonstrated three different music tasks in the paper, i.e: melody completion, accompaniment suggestion, and genre classification.
Comments