Composition by conversation (CbC) is a scenario in the MUSICA project where a human and machine collaboratively compose music primarily through the use of natural language commands. This task involves modeling natural language for musical concepts, developing computational models of music that facilitate integration with natural language processing algorithms, querying a score for musical features based on partial specifications of concepts, and generating new music based on user descriptions.
MusECI (Musical Elementary Composable Ideas) is a Python library that is a key component of MUSICAs implementations for the CbC task. It seeks to be an intermediate level of representation between those used in natural language parsing tasks and the more strictly numerical representations used for musical file formats to represent scores.
The following video showcases the new Unity interface for Composition by Conversation.