Communication Dans Un Congrès Année : 2025

F-StrIPE: Fast Structure-Informed Positional Encoding for Symbolic Music Generation

Résumé

While music remains a challenging domain for generative models like Transformers, recent progress has been made by exploiting suitable musically-informed priors. One technique to leverage information about musical structure in Transformers is inserting such knowledge into the positional encoding (PE) module. However, Transformers carry a quadratic cost in sequence length. In this paper, we propose F-StrIPE, a structure-informed PE scheme that works in linear complexity. Using existing kernel approximation techniques based on random features, we show that F-StrIPE is a generalization of Stochastic Positional Encoding (SPE). We illustrate the empirical merits of F-StrIPE using melody harmonization for symbolic music.
Fichier principal
Vignette du fichier
IEEE-conference-template-062824.pdf (1) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-04935674 , version 1 (10-02-2025)

Identifiants

Citer

Manvi Agarwal, Changhong Wang, Gael Richard. F-StrIPE: Fast Structure-Informed Positional Encoding for Symbolic Music Generation. IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Apr 2025, Hyderabad, India. ⟨hal-04935674⟩
0 Consultations
0 Téléchargements

Altmetric

Partager

More