comparative-study · yeh2021-melody-harmonization

the task of automatic melody harmonization, in which a model aims to generate a sequence of chords to serve as the harmonic accompaniment of a given multiple-bar melody sequence. [...] including a template matching based model, a hidden Markov based model, a genetic algorithm based model, and two deep learning based models. The evaluation is conducted on a dataset of 9,226 melody/chord pairs we newly collect for this study, considering up to 48 triad chords [...] and a subjective study with 202 participants. [...] Melody harmonization is a challenging task as there are multiple ways to harmonize the same melody; what makes a particular harmonization pleasant is subjective, and often dependent on musical genre and other contextual factors. [...] For Interestingness, GA performs the best among the five automatic methods [...] there is significant performance difference between the MTHarmonzer progressions and the original human-composed progressions in terms of Coherence and Chord Progression [...], but no significant difference in terms of Interestingness and Overall. [...] Our evaluation shows that deep learning models indeed perform better than non-deep learning ones in a variety of aspects, including harmonicity and interestingness. Moreover, a deep learning model that takes the function of chords into account reaches the best result among the evaluated models.