Skip to Main content Skip to Navigation
Conference papers

Estimating keys and modulations in musical pieces

Laurent Feisthauer 1, 2 Louis Bigo 1, 2 Mathieu Giraud 1, 2 Florence Levé 1, 3, 2 
1 Algomus
MIS - Modélisation, Information et Systèmes - UR UPJV 4290, CRIStAL - Centre de Recherche en Informatique, Signal et Automatique de Lille - UMR 9189
Abstract : Modulations, the moments where key change, are structurally important in tonal music. Analyzing music, especially studying large-scale music structure of a piece, often implies to look for modulations. State-of-the-art key-finding algorithms generally aim at identifying keys rather than studying the way they change. Here, we introduce new ways to model modulations with the help of features based on musicological knowledge, as well as an algorithm estimating the tonal plan of a piece. We study the concept of current diatonic pitch set and introduce a heuristic to detect dominant-to-tonic progressions. We design three proximity measures to assess how close the music is from each key. These measures are then combined by an algorithm that identifies an optimal tonal plan. We report results on a corpus including 38 movements from Mozart's string quartets, obtaining a 84.8% prediction of correct keys with insight on where the modulations occur.
Complete list of metadata

Cited literature [31 references]  Display  Hide  Download
Contributor : Mathieu Giraud Connect in order to contact the contributor
Submitted on : Wednesday, September 9, 2020 - 12:14:45 PM
Last modification on : Friday, August 5, 2022 - 11:24:59 AM


Files produced by the author(s)


Public Domain


  • HAL Id : hal-02886399, version 2


Laurent Feisthauer, Louis Bigo, Mathieu Giraud, Florence Levé. Estimating keys and modulations in musical pieces. Sound and Music Computing Conference (SMC 2020), Simone Spagnol; Andrea Valle, Jun 2020, Torino, Italy. ⟨hal-02886399v2⟩



Record views


Files downloads