MusIAC: An extensible generative framework for Music Infilling Applications with multi-level Control
This work addresses music generation for applications requiring customizable infilling, though it is incremental in extending control mechanisms.
The researchers tackled music infilling by developing a transformer-based framework with extensible control tokens for properties like tonal tension and track polyphony, demonstrating that additional tokens improve stylistic similarity to original music and provide more user control over texture and tension compared to prior work focused only on track density.
We present a novel music generation framework for music infilling, with a user friendly interface. Infilling refers to the task of generating musical sections given the surrounding multi-track music. The proposed transformer-based framework is extensible for new control tokens as the added music control tokens such as tonal tension per bar and track polyphony level in this work. We explore the effects of including several musically meaningful control tokens, and evaluate the results using objective metrics related to pitch and rhythm. Our results demonstrate that adding additional control tokens helps to generate music with stronger stylistic similarities to the original music. It also provides the user with more control to change properties like the music texture and tonal tension in each bar compared to previous research which only provided control for track density. We present the model in a Google Colab notebook to enable interactive generation.