INTERNATIONAL JOURNAL OF INTELLIGENT SYSTEMS AND DATA SCIENCE

Latent Phrase-Aware Generative Modeling for Expressive Symbolic Audio Synthesis

1.Campbellsville University

Published in issue

October 2026

Volume / Issue

Vol. 1 No. 3

Access

Open access

View PDF

The article details presented on this page reflect the published version of record. Readers may access the full-text PDF, review the citation information, and export the reference in supported citation formats.

Abstract

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.
Keywords:Phrase-Aware Latent AlignmentSymbolic Music SynthesisControllable GenerationSequence-Level RegularizationCompact TokenizationGenerative AI

Cite this Article

Use the following citation when referencing this publication in academic or professional work.

A. Bhuekar, "Latent Phrase-Aware Generative Modeling for Expressive Symbolic Audio Synthesis", Int. J. Intell. Syst. Data Sci., vol. 1, no. 3, Oct. 2026, doi: https://doi.org/10.67231/8pgacf28.

DOWNLOAD CITATION

Latent Phrase-Aware Generative Modeling for Expressive Symbolic Audio Synthesis | International Journal of Intelligent Systems and Data Science