TY - GEN
T1 - An analysis/synthesis framework for automatic f0 annotation of multitrack datasets
AU - Salamon, Justin
AU - Bittner, Rachel M.
AU - Bonada, Jordi
AU - Bosch, Juan J.
AU - Gómez, Emilia
AU - Bello, Juan Pablo
N1 - Publisher Copyright:
© 2019 Justin Salamon, Rachel M. Bittner, Jordi Bonada, Juan J. Bosch, Emilia Gómez.
PY - 2017
Y1 - 2017
N2 - 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.
AB - 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.
UR - http://www.scopus.com/inward/record.url?scp=85054290573&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85054290573&partnerID=8YFLogxK
M3 - Conference contribution
AN - SCOPUS:85054290573
T3 - Proceedings of the 18th International Society for Music Information Retrieval Conference, ISMIR 2017
SP - 71
EP - 78
BT - Proceedings of the 18th International Society for Music Information Retrieval Conference, ISMIR 2017
A2 - Cunningham, Sally Jo
A2 - Duan, Zhiyao
A2 - Hu, Xiao
A2 - Turnbull, Douglas
PB - International Society for Music Information Retrieval
T2 - 18th International Society for Music Information Retrieval Conference, ISMIR 2017
Y2 - 23 October 2017 through 27 October 2017
ER -