A software framework for musical data augmentation

Brian McFee, Eric J. Humphrey, Juan Bello

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

Abstract

Predictive models for music annotation tasks are practically limited by a paucity of well-annotated training data. In the broader context of large-scale machine learning, the concept of “data augmentation” — supplementing a training set with carefully perturbed samples — has emerged as an important component of robust systems. In this work, we develop a general software framework for augmenting annotated musical datasets, which will allow practitioners to easily expand training sets with musically motivated perturbations of both audio and annotations. As a proof of concept, we investigate the effects of data augmentation on the task of recognizing instruments in mixed signals.

Original languageEnglish (US)
Title of host publicationProceedings of the 16th International Society for Music Information Retrieval Conference, ISMIR 2015
EditorsFrans Wiering, Meinard Muller
PublisherInternational Society for Music Information Retrieval
Pages248-254
Number of pages7
ISBN (Electronic)9788460688532
StatePublished - Jan 1 2015
Event16th International Society for Music Information Retrieval Conference, ISMIR 2015 - Malaga, Spain
Duration: Oct 26 2015Oct 30 2015

Publication series

NameProceedings of the 16th International Society for Music Information Retrieval Conference, ISMIR 2015

Conference

Conference16th International Society for Music Information Retrieval Conference, ISMIR 2015
CountrySpain
CityMalaga
Period10/26/1510/30/15

Fingerprint

Learning systems
Software
Augmentation
Annotation
Machine Learning
Music

ASJC Scopus subject areas

  • Music
  • Information Systems

Cite this

McFee, B., Humphrey, E. J., & Bello, J. (2015). A software framework for musical data augmentation. In F. Wiering, & M. Muller (Eds.), Proceedings of the 16th International Society for Music Information Retrieval Conference, ISMIR 2015 (pp. 248-254). (Proceedings of the 16th International Society for Music Information Retrieval Conference, ISMIR 2015). International Society for Music Information Retrieval.

A software framework for musical data augmentation. / McFee, Brian; Humphrey, Eric J.; Bello, Juan.

Proceedings of the 16th International Society for Music Information Retrieval Conference, ISMIR 2015. ed. / Frans Wiering; Meinard Muller. International Society for Music Information Retrieval, 2015. p. 248-254 (Proceedings of the 16th International Society for Music Information Retrieval Conference, ISMIR 2015).

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

McFee, B, Humphrey, EJ & Bello, J 2015, A software framework for musical data augmentation. in F Wiering & M Muller (eds), Proceedings of the 16th International Society for Music Information Retrieval Conference, ISMIR 2015. Proceedings of the 16th International Society for Music Information Retrieval Conference, ISMIR 2015, International Society for Music Information Retrieval, pp. 248-254, 16th International Society for Music Information Retrieval Conference, ISMIR 2015, Malaga, Spain, 10/26/15.
McFee B, Humphrey EJ, Bello J. A software framework for musical data augmentation. In Wiering F, Muller M, editors, Proceedings of the 16th International Society for Music Information Retrieval Conference, ISMIR 2015. International Society for Music Information Retrieval. 2015. p. 248-254. (Proceedings of the 16th International Society for Music Information Retrieval Conference, ISMIR 2015).
McFee, Brian ; Humphrey, Eric J. ; Bello, Juan. / A software framework for musical data augmentation. Proceedings of the 16th International Society for Music Information Retrieval Conference, ISMIR 2015. editor / Frans Wiering ; Meinard Muller. International Society for Music Information Retrieval, 2015. pp. 248-254 (Proceedings of the 16th International Society for Music Information Retrieval Conference, ISMIR 2015).
@inproceedings{bc6fd1c6948a4f3781a60dc10308df40,
title = "A software framework for musical data augmentation",
abstract = "Predictive models for music annotation tasks are practically limited by a paucity of well-annotated training data. In the broader context of large-scale machine learning, the concept of “data augmentation” — supplementing a training set with carefully perturbed samples — has emerged as an important component of robust systems. In this work, we develop a general software framework for augmenting annotated musical datasets, which will allow practitioners to easily expand training sets with musically motivated perturbations of both audio and annotations. As a proof of concept, we investigate the effects of data augmentation on the task of recognizing instruments in mixed signals.",
author = "Brian McFee and Humphrey, {Eric J.} and Juan Bello",
year = "2015",
month = "1",
day = "1",
language = "English (US)",
series = "Proceedings of the 16th International Society for Music Information Retrieval Conference, ISMIR 2015",
publisher = "International Society for Music Information Retrieval",
pages = "248--254",
editor = "Frans Wiering and Meinard Muller",
booktitle = "Proceedings of the 16th International Society for Music Information Retrieval Conference, ISMIR 2015",

}

TY - GEN

T1 - A software framework for musical data augmentation

AU - McFee, Brian

AU - Humphrey, Eric J.

AU - Bello, Juan

PY - 2015/1/1

Y1 - 2015/1/1

N2 - Predictive models for music annotation tasks are practically limited by a paucity of well-annotated training data. In the broader context of large-scale machine learning, the concept of “data augmentation” — supplementing a training set with carefully perturbed samples — has emerged as an important component of robust systems. In this work, we develop a general software framework for augmenting annotated musical datasets, which will allow practitioners to easily expand training sets with musically motivated perturbations of both audio and annotations. As a proof of concept, we investigate the effects of data augmentation on the task of recognizing instruments in mixed signals.

AB - Predictive models for music annotation tasks are practically limited by a paucity of well-annotated training data. In the broader context of large-scale machine learning, the concept of “data augmentation” — supplementing a training set with carefully perturbed samples — has emerged as an important component of robust systems. In this work, we develop a general software framework for augmenting annotated musical datasets, which will allow practitioners to easily expand training sets with musically motivated perturbations of both audio and annotations. As a proof of concept, we investigate the effects of data augmentation on the task of recognizing instruments in mixed signals.

UR - http://www.scopus.com/inward/record.url?scp=84996516893&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84996516893&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:84996516893

T3 - Proceedings of the 16th International Society for Music Information Retrieval Conference, ISMIR 2015

SP - 248

EP - 254

BT - Proceedings of the 16th International Society for Music Information Retrieval Conference, ISMIR 2015

A2 - Wiering, Frans

A2 - Muller, Meinard

PB - International Society for Music Information Retrieval

ER -