English

Music Score Expansion with Variable-Length Infilling

Sound 2021-11-12 v1 Artificial Intelligence Audio and Speech Processing

Abstract

In this paper, we investigate using the variable-length infilling (VLI) model, which is originally proposed to infill missing segments, to "prolong" existing musical segments at musical boundaries. Specifically, as a case study, we expand 20 musical segments from 12 bars to 16 bars, and examine the degree to which the VLI model preserves musical boundaries in the expanded results using a few objective metrics, including the Register Histogram Similarity we newly propose. The results show that the VLI model has the potential to address the expansion task.

Cite

@article{arxiv.2111.06046,
  title  = {Music Score Expansion with Variable-Length Infilling},
  author = {Chih-Pin Tan and Chin-Jui Chang and Alvin W. Y. Su and Yi-Hsuan Yang},
  journal= {arXiv preprint arXiv:2111.06046},
  year   = {2021}
}

Comments

Going to published as a late-breaking demo paper at ISMIR 2021

R2 v1 2026-06-24T07:34:38.962Z