Vocalist gender recognition in recorded popular music

Björn Schuller, Christoph Kozielski, Felix Weninger, Florian Eyben, Gerhard Rigoll

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

9 Scopus citations

Abstract

We introduce the task of vocalist gender recognition in popular music and evaluate the benefit of Non-Negative Matrix Factorization based enhancement of melodic components to this aim. The underlying automatic separation of drum beats is described in detail, and the obtained significant gain by its use is verified in extensive test-runs on a novel database of 1.5 days of MP3 coded popular songs based on transcriptions of the Karaoke-game UltraStar. As classifiers serve Support Vector Machines and Hidden Naive Bayes. Overall, the suggested methods lead to fully automatic recognition of the pre-dominant vocalist gender at 87.31% accuracy on song level for artists unkown to the system in originally recorded music.

Original languageEnglish
Title of host publicationProceedings of the 11th International Society for Music Information Retrieval Conference, ISMIR 2010
Pages613-618
Number of pages6
StatePublished - 2010
Event11th International Society for Music Information Retrieval Conference, ISMIR 2010 - Utrecht, Netherlands
Duration: 9 Aug 201013 Aug 2010

Publication series

NameProceedings of the 11th International Society for Music Information Retrieval Conference, ISMIR 2010

Conference

Conference11th International Society for Music Information Retrieval Conference, ISMIR 2010
Country/TerritoryNetherlands
CityUtrecht
Period9/08/1013/08/10

Fingerprint

Dive into the research topics of 'Vocalist gender recognition in recorded popular music'. Together they form a unique fingerprint.

Cite this