Audio chord labeling by musiological modeling and beat-synchronization

Björn Schuller, Benedikt Hörnler, Dejan Arsic, Gerhard Rigoll

Publikation: Beitrag in Buch/Bericht/KonferenzbandKonferenzbeitragBegutachtung

3 Zitate (Scopus)

Abstract

Automatic labeling of chords in original audio recordings is challenging due to heavy acoustic overlay by melody and percussion sections, detuning and arpeggios that demand for a measure-grid to assign notes to chords. Further chord labeling benefits from contextual information. In this respect we suggest applying an HMM framework incorporating a musiological model trained on 16k songs and synchronization with the measure grid by IIR comb-filter banks for tempo detection, meter recognition, and on-beat tracking. Features base on pitch-tuned chromatic information. Extensive evaluation on 11k chords of 7h of MP3 compressed popular music demonstrates effectiveness over traditional correlation analysis and single measure classification by Support Vector Machines.

OriginalspracheEnglisch
TitelProceedings - 2009 IEEE International Conference on Multimedia and Expo, ICME 2009
Seiten526-529
Seitenumfang4
DOIs
PublikationsstatusVeröffentlicht - 2009
Veranstaltung2009 IEEE International Conference on Multimedia and Expo, ICME 2009 - New York, NY, USA/Vereinigte Staaten
Dauer: 28 Juni 20093 Juli 2009

Publikationsreihe

NameProceedings - 2009 IEEE International Conference on Multimedia and Expo, ICME 2009

Konferenz

Konferenz2009 IEEE International Conference on Multimedia and Expo, ICME 2009
Land/GebietUSA/Vereinigte Staaten
OrtNew York, NY
Zeitraum28/06/093/07/09

Fingerprint

Untersuchen Sie die Forschungsthemen von „Audio chord labeling by musiological modeling and beat-synchronization“. Zusammen bilden sie einen einzigartigen Fingerprint.

Dieses zitieren