Archive
IJMSTA - Vol. 7 - Issue 2 - July 2025
ISSN 2612-2146
Pages: 16
Style-Specific Melody Harmonization via Multi-Objective Optimization
Authors: Stephanie Y. H. Lew, Wee Kheng Leow, Kat R. Agres
Categories: Journal
Abstract - Style-specific harmonization aims at generating a chord sequence that matches a given melody in a specific style. Existing methods for generating chord sequence have some shortcomings. Most of them are trained on a large training set of a specific genre such as pop or jazz. To accommodate to different styles, they need to train a different version of the method on a different style-specific training set, increasing the total training time. If they are trained on a mixed-style set that contains examples of various styles, they will mix up the styles and produce results that are diluted in style. Moreover, existing methods cannot cater to cadence and voice leading. Many recent deep neural networks (DNNs) for harmonization are tested on 8-bar phrases instead of complete music pieces. While this makes testing easier, they cannot handle the global structure of music which lead to better overall harmonic coherence. This paper proposes a style-specific harmonization method called FlexChord that overcomes the shortcomings of existing methods. FlexChord achieves style specificity by producing chord sequence that matches the style of a selected set of example music, which can be as little as a single example music piece. It applies direct optimization during chord generation that does not require training. Thus, it can easily produce chord sequence of a specific style or a custom style. The requirement of cleaning, annotating and training on large datasets is avoided. In addition, FlexChord can handle cadence and voice leading effectively. It can generate chords that match full-length melodies, complete with global music structure. Test results show that FlexChord's harmonization is better than those of comparable DNNs and is close to that of human harmonization.
Keywords: Chord generation, Harmonization, Multi-objective optimization, Style-specificity
Download paper
