EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Cognitive encoding modeling of musical sequences for vocal performance and intelligent music composition

Shaojie Lin, Guang Zeng

Frontiers in Psychology · 24.07.2026 · 17

DOI: 10.3389/fpsyg.2026.1768708 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Frontiers in Psychology, online erschienen am 24.07.2026. Verfasst von Shaojie Lin und 1 weiteren Autor:innen. Beteiligte Einrichtung: School of Music and Dance, Tianshui Normal University, Tianshui, Gansu, China. Die Arbeit nennt 50 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Introduction

The cognitive encoding of musical sequences is a complex process that involves capturing the intricate structure, temporal dynamics, and inherent uncertainties of musical data. Traditional methods often struggle to preserve the non-Euclidean geometric properties of musical sequences and fail to adequately model temporal dependencies and uncertainties. This paper introduces the Manifold Adaptive Sequence Encoder (MASE), a novel neural framework designed to address these challenges.

Methods

MASE integrates three key modules: the Riemannian Trajectory Mapper, which embeds musical sequences into a Riemannian manifold to maintain their geometric properties; the Agent-driven Temporal Planner, which effectively models the temporal dependencies and rhythmic patterns; and the Uncertainty-guided Sequence Filter, which quantifies and incorporates uncertainty to enhance robustness and generalization. The framework is optimized using manifold alignment optimization, ensuring the alignment of latent representations with the input data, and uncertainty-aware refinement, which iteratively refines predictions by leveraging uncertainty estimates. Results and discussion Experimental results demonstrate that MASE significantly improves the accuracy and robustness of musical sequence modeling, outperforming existing methods by a substantial margin. The proposed approach offers a principled methodology for modeling the cognitive encoding of musical sequences, with potential applications in music analysis, recommendation, and generation. This advancement in musical sequence encoding not only enhances the understanding of cognitive processes involved in music perception but also provides a robust tool for various practical applications in the field of music technology.

Schlagwörter

Stichwörter der Autor:innen

Manifold Adaptive Sequence Encoder (MASE)Riemannian Trajectory Mappercognitive encoding of musical sequencestemporal dependencies and rhythmic patternsuncertainty-aware refinement

Autor:innen und Institutionen

  • School of Music and Dance, Tianshui Normal University, Tianshui, Gansu, China.

Zitieren

APA

Lin, S., & Zeng, G. (2026). Cognitive encoding modeling of musical sequences for vocal performance and intelligent music composition. Frontiers in Psychology, 17. https://doi.org/10.3389/fpsyg.2026.1768708

Vancouver

Lin S, Zeng G. Cognitive encoding modeling of musical sequences for vocal performance and intelligent music composition. Frontiers in Psychology. 2026;17. doi:10.3389/fpsyg.2026.1768708

BibTeX
@article{Lin2026,
  author = {Lin, Shaojie and Zeng, Guang},
  title = {Cognitive encoding modeling of musical sequences for vocal performance and intelligent music composition},
  journal = {Frontiers in Psychology},
  year = {2026},
  volume = {17},
  doi = {10.3389/fpsyg.2026.1768708}
}
Kostenlos starten →