Work

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

Year: 2025

Type: conference-paper

Abstract: 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.

Source: IEEE International Conference on Acoustics Speech and Signal Processing

DOI: 10.1109/icassp49660.2025.10888904

Authors: Manvi Agarwal, Changhong Wang, Gaël Richard

Institutions: Télécom Paris, Institut Polytechnique de Paris, Laboratoire Traitement et Communication de l’Information

Language: English

Topic: Music Technology and Sound Studies

Subfield: Computer Vision and Pattern Recognition

Field: Computer Science

Domain: Physical Sciences

Open Access status: green

OpenAlex ID: W4407559316

FWCI: 0.781

Cites: 29

Cited by: 1

Related to: 10