arXiv Open Access 2024

Structure-informed Positional Encoding for Music Generation

Manvi Agarwal Changhong Wang Gaël Richard
Lihat Sumber

Abstrak

Music generated by deep learning methods often suffers from a lack of coherence and long-term organization. Yet, multi-scale hierarchical structure is a distinctive feature of music signals. To leverage this information, we propose a structure-informed positional encoding framework for music generation with Transformers. We design three variants in terms of absolute, relative and non-stationary positional information. We comprehensively test them on two symbolic music generation tasks: next-timestep prediction and accompaniment generation. As a comparison, we choose multiple baselines from the literature and demonstrate the merits of our methods using several musically-motivated evaluation metrics. In particular, our methods improve the melodic and structural consistency of the generated pieces.

Topik & Kata Kunci

Penulis (3)

M

Manvi Agarwal

C

Changhong Wang

G

Gaël Richard

Format Sitasi

Agarwal, M., Wang, C., Richard, G. (2024). Structure-informed Positional Encoding for Music Generation. https://arxiv.org/abs/2402.13301

Akses Cepat

Lihat di Sumber
Informasi Jurnal
Tahun Terbit
2024
Bahasa
en
Sumber Database
arXiv
Akses
Open Access ✓