Measure by Measure: Measure-Based Automatic Music Composition with Modern Staff Notation

This paper introduces a hierarchical framework for automatic composition of polyphonic music in Western modern staff notation. Central to our framework, a music score is represented as a grid of part‑wise measures, where each measure is encoded using dual representations: a vector summarizing the content and a matrix facilitating alignment between different parts. This is achieved by designing a measure encoder–decoder, i.e., the measure model, that directly mirrors the object hierarchy of a part‑wise measure in modern staff notation. This grid‑like representation enables music generation algorithms to model temporal dependencies directly at the level of measures. We then demonstrate the application of our measure model using two generation paradigms: autoregressive models and conditionally specified distributions https://github.com/Yujia-Yan/Measure_By_Measure.