Composition by Conversation

TL;DR

The paper introduces MusECI, a framework that combines musical programming, query languages, and natural language processing to enable conversational composition at the score level within a text editor.

Contribution

It presents a novel framework that unifies musical programming and query languages with NLP models to facilitate composition through conversation.

Findings

Prototype framework MusECI demonstrated effective score-level composition.

Connectivity to NLP frameworks enables natural language interaction.

Framework bridges musical programming and conversational interfaces.

Abstract

Most musical programming languages are developed purely for coding virtual instruments or algorithmic compositions. Although there has been some work in the domain of musical query languages for music information retrieval, there has been little attempt to unify the principles of musical programming and query languages with cognitive and natural language processing models that would facilitate the activity of composition by conversation. We present a prototype framework, called MusECI, that merges these domains, permitting score-level algorithmic composition in a text editor while also supporting connectivity to existing natural language processing frameworks.