Table of Contents
Fetching ...

ComposeOn Academy: Transforming Melodic Ideas into Complete Compositions Integrating Music Learning

Hongxi Pu, Futian Jiang, Zihao Chen, Xingyue Song

TL;DR

ComposeOn addresses the barrier that novice users face when creating music with traditional DAWs by introducing a music-theory–based system that extends melodies into complete compositions while teaching music theory. The approach integrates melody input, a chord/rhythm database, pitch analysis via Basic Pitch, and a three-step generation process informed by functional and tonal harmony, with explanations at multiple proficiency levels and a Music Theory Mentor. A user study (N=10) shows ComposeOn outperforms a Suno AI baseline in coherence, structure, and learner engagement, driven by high visualization, interactivity, and explainability. The work demonstrates that theory-based composition tools can function as effective music-education platforms, bridging theory and practice and informing future hybrids that combine educational insight with generative creativity.

Abstract

Music composition has long been recognized as a significant art form. However, existing digital audio workstations and music production software often present high entry barriers for users lacking formal musical training. To address this, we introduce ComposeOn, a music theory-based tool designed for users with limited musical knowledge. ComposeOn enables users to easily extend their melodic ideas into complete compositions and offers simple editing features. By integrating music theory, it explains music creation at beginner, intermediate, and advanced levels. Our user study (N=10) compared ComposeOn with the baseline method, Suno AI, demonstrating that ComposeOn provides a more accessible and enjoyable composing and learning experience for individuals with limited musical skills. ComposeOn bridges the gap between theory and practice, offering an innovative solution as both a composition aid and music education platform. The study also explores the differences between theory-based music creation and generative music, highlighting the former's advantages in personal expression and learning.

ComposeOn Academy: Transforming Melodic Ideas into Complete Compositions Integrating Music Learning

TL;DR

ComposeOn addresses the barrier that novice users face when creating music with traditional DAWs by introducing a music-theory–based system that extends melodies into complete compositions while teaching music theory. The approach integrates melody input, a chord/rhythm database, pitch analysis via Basic Pitch, and a three-step generation process informed by functional and tonal harmony, with explanations at multiple proficiency levels and a Music Theory Mentor. A user study (N=10) shows ComposeOn outperforms a Suno AI baseline in coherence, structure, and learner engagement, driven by high visualization, interactivity, and explainability. The work demonstrates that theory-based composition tools can function as effective music-education platforms, bridging theory and practice and informing future hybrids that combine educational insight with generative creativity.

Abstract

Music composition has long been recognized as a significant art form. However, existing digital audio workstations and music production software often present high entry barriers for users lacking formal musical training. To address this, we introduce ComposeOn, a music theory-based tool designed for users with limited musical knowledge. ComposeOn enables users to easily extend their melodic ideas into complete compositions and offers simple editing features. By integrating music theory, it explains music creation at beginner, intermediate, and advanced levels. Our user study (N=10) compared ComposeOn with the baseline method, Suno AI, demonstrating that ComposeOn provides a more accessible and enjoyable composing and learning experience for individuals with limited musical skills. ComposeOn bridges the gap between theory and practice, offering an innovative solution as both a composition aid and music education platform. The study also explores the differences between theory-based music creation and generative music, highlighting the former's advantages in personal expression and learning.

Paper Structure

This paper contains 26 sections, 3 figures, 2 tables.

Figures (3)

  • Figure 1: ComposeOn System Design Diagram: the input and analysis module, represented by light-blue color; the generation module, represented by light-green color; and the output and explanation module, represented by light-yellow color.
  • Figure 2: ComposeOn UI illustration. Step1-2, choose a file, and process the file as MIDI. Step3-4, when click on the continue button, a new progression will be added. Step 5-6, click one bar or some notes to check the explanation. Step 7, click the hyperlink for quick chat with a chatbot powered by ChatGPT 4. Step8-9, check the alternative rhythms and chords suitable for the selected bar.
  • Figure 3: 5-point result on the music theory correctness and the subjective assessments.