An analysis/synthesis framework for automatic f0 annotation of multitrack datasets

Justin Salamon, Rachel M. Bittner, Jordi Bonada, Juan J. Bosch, Emilia Gómez, Juan Pablo Bello

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

Abstract

Generating continuous f0 annotations for tasks such as melody extraction and multiple f0 estimation typically involves running a monophonic pitch tracker on each track of a multitrack recording and manually correcting any estimation errors. This process is labor intensive and time consuming, and consequently existing annotated datasets are very limited in size. In this paper we propose a framework for automatically generating continuous f0 annotations without requiring manual refinement: the estimate of a pitch tracker is used to drive an analysis/synthesis pipeline which produces a synthesized version of the track. Any estimation errors are now reflected in the synthesized audio, meaning the tracker's output represents an accurate annotation. Analysis is performed using a wide-band harmonic sinusoidal modeling algorithm which estimates the frequency, amplitude and phase of every harmonic, meaning the synthesized track closely resembles the original in terms of timbre and dynamics. Finally the synthesized track is automatically mixed back into the multitrack. The framework can be used to annotate multitrack datasets for training learning-based algorithms. Furthermore, we show that algorithms evaluated on the automatically generated/annotated mixes produce results that are statistically indistinguishable from those they produce on the original, manually annotated, mixes. We release a software library implementing the proposed framework, along with new datasets for melody, bass and multiple f0 estimation.

Original languageEnglish (US)
Title of host publicationProceedings of the 18th International Society for Music Information Retrieval Conference, ISMIR 2017
EditorsSally Jo Cunningham, Zhiyao Duan, Xiao Hu, Douglas Turnbull
PublisherInternational Society for Music Information Retrieval
Pages71-78
Number of pages8
ISBN (Electronic)9789811151798
StatePublished - 2017
Event18th International Society for Music Information Retrieval Conference, ISMIR 2017 - Suzhou, China
Duration: Oct 23 2017Oct 27 2017

Publication series

NameProceedings of the 18th International Society for Music Information Retrieval Conference, ISMIR 2017

Conference

Conference18th International Society for Music Information Retrieval Conference, ISMIR 2017
Country/TerritoryChina
CitySuzhou
Period10/23/1710/27/17

ASJC Scopus subject areas

  • Music
  • Information Systems

Fingerprint

Dive into the research topics of 'An analysis/synthesis framework for automatic f0 annotation of multitrack datasets'. Together they form a unique fingerprint.

Cite this