![]() Furthermore, for R3, we can leverage the evolution from chord to chord progression to bridge between texture and form, which contributes to the joint learning of the two structures.Īs for the end-to-end generators mining the structure adaptively, in StructureNet StructureNet-2018, the authors leverage the RNN to exploit the structural repeat in the music. Therefore, harmony is potential to be an appropriate musical structure units. And in the end of the music, there exists a common harmonic cadence “V-I” cadence-1999, which reveals the important role of the harmony in the structure. For example, in Figure 0(b), the chord progressions usually repeat among the different phrases or sections. Besides, the other participant, chord progression, usually promotes the development of the music, contributing to the formation of the form. As the red hollow blocks in Figure 0(a) show, the accompaniment textures always appear in chords. Specifically, one of the participants of harmony, chord, represents the harmonic set of multiple notes, which is integrated closely with the texture. For R2, not only harmony itself is an important structure element, but also it combines the many musical elements organically, from the low-level notes to the high-level phrase and sections. The reasons to learn harmony are that for R1, harmony represents the consonance of the musical context, so we can mine the musical contextual information by learning it. 4 4 4In musicology, the study of harmony involves chords and their construction, and chord progressions and the principles of connection that govern them harmony-dictionary. \affiliationsīased on the aforementioned requirements, we propose to leverage harmony-aware learning for structure-enhanced pop music generation. Results of subjective and objective evaluations demonstrate that HAT significantly improves the quality of generated music, especially in the structureness. Furthermore, we propose the Harmony- Aware Hierarchical Music Transformer (HAT), which can exploit the structure adaptively from the music, and interact on the music tokens at multiple levels to enhance the signals of the structure in various musical elements. Besides, when chords evolve into chord progression, the texture and the form can be bridged by the harmony naturally, which contributes to the joint learning of the two structures. On the other hand, the other participant of harmony, chord progression, usually accompanies with the development of the music, which promotes the temporal structure of music, form. On the one hand, one of the participants of harmony, chord, represents the harmonic set of multiple notes, which is integrated closely with the spatial structure of music, texture. In this paper, we propose to leverage harmony-aware learning for structure-enhanced pop music generation. And it is still far from being solved that how we should model the structure in pop music generation. Although the musical structure is easy to be perceived by human, it is difficult to be described clearly and defined accurately. Automatically composing pop music with a satisfactory structure is an attractive but challenging topic.
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |