Moving beyond feature design: Deep architectures and automatic feature learning in music informatics

Eric J. Humphrey, Juan Pablo Bello, Yann LeCun

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

Abstract

The short history of content-based music informatics research is dominated by hand-crafted feature design, and our community has grown admittedly complacent with a few de facto standards. Despite commendable progress in many areas, it is increasingly apparent that our efforts are yielding diminishing returns. This deceleration is largely due to the tandem of heuristic feature design and shallow processing architectures. We systematically discard hopefully irrelevant information while simultaneously calling upon creativity, intuition, or sheer luck to craft useful representations, gradually evolving complex, carefully tuned systems to address specific tasks. While other disciplines have seen the benefits of deep learning, it has only recently started to be explored in our field. By reviewing deep architectures and feature learning, we hope to raise awareness in our community about alternative approaches to solving MIR challenges, new and old alike.

Original languageEnglish (US)
Title of host publicationProceedings of the 13th International Society for Music Information Retrieval Conference, ISMIR 2012
Pages403-408
Number of pages6
StatePublished - 2012
Event13th International Society for Music Information Retrieval Conference, ISMIR 2012 - Porto, Portugal
Duration: Oct 8 2012Oct 12 2012

Other

Other13th International Society for Music Information Retrieval Conference, ISMIR 2012
CountryPortugal
CityPorto
Period10/8/1210/12/12

Fingerprint

Deceleration
Processing
Music
Informatics
Deep learning
Intuition
History
Heuristics
Creativity
Reviewing
Luck

ASJC Scopus subject areas

  • Music
  • Information Systems

Cite this

Humphrey, E. J., Bello, J. P., & LeCun, Y. (2012). Moving beyond feature design: Deep architectures and automatic feature learning in music informatics. In Proceedings of the 13th International Society for Music Information Retrieval Conference, ISMIR 2012 (pp. 403-408)

Moving beyond feature design : Deep architectures and automatic feature learning in music informatics. / Humphrey, Eric J.; Bello, Juan Pablo; LeCun, Yann.

Proceedings of the 13th International Society for Music Information Retrieval Conference, ISMIR 2012. 2012. p. 403-408.

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

Humphrey, EJ, Bello, JP & LeCun, Y 2012, Moving beyond feature design: Deep architectures and automatic feature learning in music informatics. in Proceedings of the 13th International Society for Music Information Retrieval Conference, ISMIR 2012. pp. 403-408, 13th International Society for Music Information Retrieval Conference, ISMIR 2012, Porto, Portugal, 10/8/12.
Humphrey EJ, Bello JP, LeCun Y. Moving beyond feature design: Deep architectures and automatic feature learning in music informatics. In Proceedings of the 13th International Society for Music Information Retrieval Conference, ISMIR 2012. 2012. p. 403-408
Humphrey, Eric J. ; Bello, Juan Pablo ; LeCun, Yann. / Moving beyond feature design : Deep architectures and automatic feature learning in music informatics. Proceedings of the 13th International Society for Music Information Retrieval Conference, ISMIR 2012. 2012. pp. 403-408
@inproceedings{caed50e69869454c9548ed7d8d448afb,
title = "Moving beyond feature design: Deep architectures and automatic feature learning in music informatics",
abstract = "The short history of content-based music informatics research is dominated by hand-crafted feature design, and our community has grown admittedly complacent with a few de facto standards. Despite commendable progress in many areas, it is increasingly apparent that our efforts are yielding diminishing returns. This deceleration is largely due to the tandem of heuristic feature design and shallow processing architectures. We systematically discard hopefully irrelevant information while simultaneously calling upon creativity, intuition, or sheer luck to craft useful representations, gradually evolving complex, carefully tuned systems to address specific tasks. While other disciplines have seen the benefits of deep learning, it has only recently started to be explored in our field. By reviewing deep architectures and feature learning, we hope to raise awareness in our community about alternative approaches to solving MIR challenges, new and old alike.",
author = "Humphrey, {Eric J.} and Bello, {Juan Pablo} and Yann LeCun",
year = "2012",
language = "English (US)",
isbn = "9789727521449",
pages = "403--408",
booktitle = "Proceedings of the 13th International Society for Music Information Retrieval Conference, ISMIR 2012",

}

TY - GEN

T1 - Moving beyond feature design

T2 - Deep architectures and automatic feature learning in music informatics

AU - Humphrey, Eric J.

AU - Bello, Juan Pablo

AU - LeCun, Yann

PY - 2012

Y1 - 2012

N2 - The short history of content-based music informatics research is dominated by hand-crafted feature design, and our community has grown admittedly complacent with a few de facto standards. Despite commendable progress in many areas, it is increasingly apparent that our efforts are yielding diminishing returns. This deceleration is largely due to the tandem of heuristic feature design and shallow processing architectures. We systematically discard hopefully irrelevant information while simultaneously calling upon creativity, intuition, or sheer luck to craft useful representations, gradually evolving complex, carefully tuned systems to address specific tasks. While other disciplines have seen the benefits of deep learning, it has only recently started to be explored in our field. By reviewing deep architectures and feature learning, we hope to raise awareness in our community about alternative approaches to solving MIR challenges, new and old alike.

AB - The short history of content-based music informatics research is dominated by hand-crafted feature design, and our community has grown admittedly complacent with a few de facto standards. Despite commendable progress in many areas, it is increasingly apparent that our efforts are yielding diminishing returns. This deceleration is largely due to the tandem of heuristic feature design and shallow processing architectures. We systematically discard hopefully irrelevant information while simultaneously calling upon creativity, intuition, or sheer luck to craft useful representations, gradually evolving complex, carefully tuned systems to address specific tasks. While other disciplines have seen the benefits of deep learning, it has only recently started to be explored in our field. By reviewing deep architectures and feature learning, we hope to raise awareness in our community about alternative approaches to solving MIR challenges, new and old alike.

UR - http://www.scopus.com/inward/record.url?scp=84873453413&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84873453413&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:84873453413

SN - 9789727521449

SP - 403

EP - 408

BT - Proceedings of the 13th International Society for Music Information Retrieval Conference, ISMIR 2012

ER -