Bayesian audio-to-score alignment based on joint inference of Timbre, Volume, Tempo, and note onset timings

Akira Maezawa, Hiroshi G. Okuno

Research output: Contribution to journalArticle

3 Citations (Scopus)


This article presents an offline method for aligning an audio signal to individual instrumental parts constituting a musical score. The proposed method is based on fitting multiple hidden semi-Markov models (HSMMs) to the observed audio signal. The emission probability of each state of the HSMM is described using latent harmonic allocation (LHA), a Bayesian model of a harmonic sound mixture. Each HSMM corresponds to one musical instrument's part, and the state duration probability is conditioned on a linear dynamics system (LDS) tempo model. Variational Bayesian inference is used to jointly infer LHA, HSMM, and the LDS. We evaluate the capability of the method to align musical audio to its score, under reverberation, structural variations, and fluctuations in onset timing among different parts.

Original languageEnglish
Pages (from-to)74-87
Number of pages14
JournalComputer Music Journal
Issue number1
Publication statusPublished - 2015 Mar 27
Externally publishedYes


ASJC Scopus subject areas

  • Computer Science Applications
  • Media Technology
  • Music

Cite this