Accurate estimation of tone duration in Automatic music transcription

Noboru Funakoshi, Toshiyuki Tanaka

Research output: Chapter in Book/Report/Conference proceedingConference contribution


Although the recent research in the field of Automatic music transcription has been active, there are still outstanding problems. Amongst, we focused on note-length and aim to estimate note-length exactly. In the past, Fourier or Wavelet transform are used to transform music signal into frequency domain. However, these transform can lose accuracy in time component. In this paper, we estimate tone duration from music signal without transforming it into frequency domain.

Original languageEnglish
Title of host publicationProceedings of SICE Annual Conference 2010, SICE 2010 - Final Program and Papers
PublisherSociety of Instrument and Control Engineers (SICE)
Number of pages3
ISBN (Print)9784907764364
Publication statusPublished - 2010 Jan 1

Publication series

NameProceedings of the SICE Annual Conference


  • Automatic music transcription
  • Correlation
  • Music note-length extract
  • Short-time Fourier transform

ASJC Scopus subject areas

  • Control and Systems Engineering
  • Computer Science Applications
  • Electrical and Electronic Engineering


Dive into the research topics of 'Accurate estimation of tone duration in Automatic music transcription'. Together they form a unique fingerprint.

Cite this