Automatic piano transcription using frequency and time-domain information

Juan P. Bello, Laurent Daudet, Mark B. Sandler

Research output: Contribution to journalArticle

Abstract

The aim of this paper is to propose solutions to some problems that arise in automatic polyphonic transcription of recorded piano music. First, we propose a method that groups spectral information in the frequency-domain and uses a rule-based framework to deal with the known problems of polyphony and harmonicity. Then, we present a novel method for multipitch-estimation that uses both frequency and time-domain information. It assumes signal segments to be the linearly weighted sum of waveforms in a database of individual piano notes. We propose a solution to the problem of generating those waveforms, by using the frequency-domain approach. We show that accurate time-domain transcription can be achieved given an adequate estimation of the database. This suggests an alternative to common frequency-domain approaches that does not require any prior training on a separate database of isolated notes

Original languageEnglish (US)
Article number1709911
Pages (from-to)2242-2251
Number of pages10
JournalIEEE Transactions on Audio, Speech and Language Processing
Volume14
Issue number6
DOIs
StatePublished - Nov 2006

Keywords

  • Audio
  • F0 estimation
  • Multiple pitch estimation
  • Music

ASJC Scopus subject areas

  • Acoustics and Ultrasonics
  • Electrical and Electronic Engineering

Fingerprint Dive into the research topics of 'Automatic piano transcription using frequency and time-domain information'. Together they form a unique fingerprint.

  • Cite this