The Interpretation Gap in Text-to-Music Generation Models
This addresses the problem of ineffective human-AI musical collaboration for musicians and researchers, but it is incremental as it builds on existing models without major breakthroughs.
The paper tackles the limited collaboration between text-to-music generation models and human musicians by identifying the interpretation stage as the primary gap, proposing strategies to address it and calling for community action.
Large-scale text-to-music generation models have significantly enhanced music creation capabilities, offering unprecedented creative freedom. However, their ability to collaborate effectively with human musicians remains limited. In this paper, we propose a framework to describe the musical interaction process, which includes expression, interpretation, and execution of controls. Following this framework, we argue that the primary gap between existing text-to-music models and musicians lies in the interpretation stage, where models lack the ability to interpret controls from musicians. We also propose two strategies to address this gap and call on the music information retrieval community to tackle the interpretation challenge to improve human-AI musical collaboration.