EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Latent Phrase-Aware Generative Modeling for Expressive Symbolic Audio Synthesis

Apeksha Bhuekar

International Journal of Intelligent Systems and Data Science · 29.06.2026 · 1 (3)

DOI: 10.67231/8pgacf28 ↗

Kurz gefasst

Fachartikel in der Zeitschrift International Journal of Intelligent Systems and Data Science, online erschienen am 29.06.2026. Verfasst von Apeksha Bhuekar. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Constructing expressive symbolic music is a hard task. A good generator must take into account long-range musical structure and fine-grained performance features at the same time. Traditional sequence-based methods typically focus on pitch and timing information while providing limited support for expressive techniques such as bends, slides, vibrato and dynamic articulation. In this paper, we propose a novel generative framework that employs a compact tokenization scheme and phrase-aware latent alignment mechanism to enhance the quality and controllability of symbolic audio synthesis. The tokenization scheme efficiently represents both basic musical events and expressive performance attributes with a limited vocabulary, resulting in substantial computational savings without semantic loss. The phrase-level latent representations are injected into the transformer attention through a KL-divergence-based bias, such that variable-length musical phrases' structural dependencies can be learned. By applying sequence regularization and a repetition-aware loss, a multi-objective optimization framework enhances generation quality by minimizing redundant expressive patterns. Through experimental evaluation on a guitar tablature dataset, we show that our model surpasses established transformer-based baselines on a number of aspects: perplexity, diversity, speed, and expressiveness. These findings prove the proposed framework’s efficiency in generating coherence, expressiveness and computational efficiency in symbolic music.

Zitieren

APA

Bhuekar, A. (2026). Latent Phrase-Aware Generative Modeling for Expressive Symbolic Audio Synthesis. International Journal of Intelligent Systems and Data Science, 1(3). https://doi.org/10.67231/8pgacf28

Vancouver

Bhuekar A. Latent Phrase-Aware Generative Modeling for Expressive Symbolic Audio Synthesis. International Journal of Intelligent Systems and Data Science. 2026;1(3). doi:10.67231/8pgacf28

BibTeX
@article{Bhuekar2026,
  author = {Bhuekar, Apeksha},
  title = {Latent Phrase-Aware Generative Modeling for Expressive Symbolic Audio Synthesis},
  journal = {International Journal of Intelligent Systems and Data Science},
  year = {2026},
  volume = {1},
  number = {3},
  doi = {10.67231/8pgacf28}
}
Kostenlos starten →