Audio chord labeling by musiological modeling and beat-synchronization

Authors:
Björn Schuller;Benedikt Hörnler;Dejan Arsic;Gerhard Rigoll
Affiliations:
Institute for Human-Machine Communication, Technische Universität München, Germany;Institute for Human-Machine Communication, Technische Universität München, Germany;Institute for Human-Machine Communication, Technische Universität München, Germany;Institute for Human-Machine Communication, Technische Universität München, Germany
Venue:
ICME'09 Proceedings of the 2009 IEEE international conference on Multimedia and Expo
Year:
2009

Citing 2
Cited 1

Tango or Waltz?: putting ballroom dance style into tempo detection

EURASIP Journal on Audio, Speech, and Music Processing - Intelligent Audio, Speech, and Music Processing Applications
Music thumbnailing incorporating harmony- and rhythm structure

AMR'08 Proceedings of the 6th international conference on Adaptive Multimedia Retrieval: identifying, Summarizing, and Recommending Image and Music

Determination of nonprototypical valence and arousal in popular music: features and performances

EURASIP Journal on Audio, Speech, and Music Processing - Special issue on scalable audio-content analysis

Quantified Score

Hi-index	0.00

Visualization

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.