DECIBEL: Improving Audio Chord Estimation for Popular Music by Alignment and Integration of Crowd-Sourced Symbolic Representations

Abstract

Automatic Chord Estimation (ace) is a fundamental task in Music Information Retrieval (mir), which has applications in both music performance and in research on other mir tasks. The ace task consists of segmenting a music recording or score and assigning a chord label to each segment. Ace has been a task in the mirex competition for 10 years, but is not yet a solved problem: current methods seem to have reached a glass ceiling. Moreover, many recent methods are trained on a limited data set and consequently suffer from overfitting. In this study, we propose decibel 1 (DEtection of Chords Improved By Exploiting Linking symbolic formats), a novel system that utilizes multiple symbolic music representations in addition to audio in order to improve ace on popular music.