MUSICA: Musical Improvising Collaborative Agent
Abstract
The goals of DARPA Communicating with Computers program are to advance the state of the art in text and video analytics to the extent that the machine and the human operator have the same mental model. This requires that the machine be able to understand the human intent, and that can explain back, to the human, in ways that makes use of the context and prior knowledge. Three challenge problems were chosen: Block world, Bio curation and Story generation. Furthermore, an Offeror could choose to address five different task areas: TA l - apparatus for the block world, TA2 - Elementary Composable Ideas, TA3 - Composition of Ideas that takes context into account, TA4 - What to say or Do and TAS ¥á Evaluation. The Offeror s task is to address TA2, TA3 and TA4 but with a slightly different task¥á that of creating music with a machine. The proposed research includes: (a) the construction of a system for representing knowledge about musical structures based on elementary composable image schemas; (b) the collection and analysis of a corpus of improvised performances by human musicians. This corpus will be analyzed in image schematic terms in order to construct a knowledge base supporting context---aware musical communication; and (c) the engineering of an interactive music performance system that integrates (a) and (b) above to make symmetric real¥¥¥time decisions in response to a human performer to create a sonic outcome recognizable as collaboratively-¥-produced music. The work will be evaluated in the context of program wide evaluation.
Document Details
- Document Type
- DoD Grant Award
- Publication Date
- Sep 11, 2018
- Source ID
- W911NF1610567
Entities
People
- Kelland Thomas
Organizations
- Army Contracting Command
- Defense Advanced Research Projects Agency
- Stevens Institute of Technology