P7-08: Symbolic Music Representations for Classification Tasks: A Systematic Evaluation
Huan Zhang (Queen Mary University of London)*, Emmanouil Karystinaios (Johannes Kepler University), Simon Dixon (Queen Mary University of London), Gerhard Widmer (Johannes Kepler University), Carlos Eduardo Cancino-Chacón (Johannes Kepler University Linz)
Subjects (starting with primary): MIR fundamentals and methodology -> symbolic music processing ; Knowledge-driven approaches to MIR -> representations of music ; MIR tasks -> automatic classification ; Musical features and properties -> representations of music ; Evaluation, datasets, and reproducibility -> evaluation methodology ; Knowledge-driven approaches to MIR -> machine learning/artificial intelligence for music
Presented Virtually: 4-minute short-format presentation
Music Information Retrieval (MIR) has seen a recent surge in deep learning-based approaches, which often involve encoding symbolic music (i.e., music represented in terms of discrete note events) in an image-like or language-like fashion. However, symbolic music is neither an image nor a sentence intrinsically, and research in the symbolic domain is lacking a comprehensive overview of the different available representations. In this paper, we investigate matrix (piano roll), sequence, and graph representations and their corresponding neural architectures, in combination with symbolic scores and performances on three piece-level classification tasks. We also introduce a novel graph representation for symbolic performances and explore the capability of graph representations in global classification tasks. Our systematic evaluation shows advantages and limitations of each input representation.
Poster session Zoom meeting
If the video does not load properly please use the direct link to video