Libretto is a new agent-facing symbolic music framework that equips LLMs with explicit grammar and corpus-calibrated statistical axes to enable measurable generation, gap-filling, morphing, and self-revision.
Learning-based methods for comparing se- quences, with applications to audio-to-midi alignment and matching,
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
fields
cs.SD 3years
2026 3verdicts
UNVERDICTED 3representative citing papers
Introduces the first large-scale Persian music dataset and shows fine-tuned MusicGen produces compositions more aligned with Persian stylistic conventions via tag-based evaluation.
A CLAP-based timbre trait predictor reaches r=0.66 correlation with human ratings on real instruments and produces the same synthesizer ranking as FAD while allowing per-sound trait analysis.
citing papers explorer
-
Libretto: Giving LLM Agents a Sense of Musical Structure
Libretto is a new agent-facing symbolic music framework that equips LLMs with explicit grammar and corpus-calibrated statistical axes to enable measurable generation, gap-filling, morphing, and self-revision.
-
Persian MusicGen: A Large-Scale Dataset and Culturally-Aware Generative Model for Persian Music
Introduces the first large-scale Persian music dataset and shows fine-tuned MusicGen produces compositions more aligned with Persian stylistic conventions via tag-based evaluation.
-
Predicting Timbre Traits for Interpretable Assessment of Musical Sound Synthesizers
A CLAP-based timbre trait predictor reaches r=0.66 correlation with human ratings on real instruments and produces the same synthesizer ranking as FAD while allowing per-sound trait analysis.