Year: 2026
Type: conference-paper
Abstract: We present Text2midi-InferAlign, a novel technique for improving symbolic music generation at inference time. Our method leverages text-to-audio and music-structural alignment rewards to guide the generation process, encouraging consistency with the input caption. Specifically, we introduce two objective scores: a text-audio consistency score measuring rhythmic and semantic alignment, and a harmonic-consistency score penalizing notes outside the musical key. By optimizing these objectives during generation using a reward-guided tree search, our model produces symbolic music more faithful to the input captions. Our approach can extend any existing autoregressive model without requiring retraining. We evaluate our work on top of the Text2midi model, demonstrating significant improvements in both objective and subjective metrics.
Authors: Abhinaba Roy, Geeta Puri, Dorien Herremans
Institution: Singapore University of Technology and Design
Language: English
Subfield: Computer Vision and Pattern Recognition
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W4417301638