ABSTRACT
REVIVE explores the affordances of live interaction between the artificial musical agent MASOM, human electronic musicians, and visual generation agents. The Musical Agent based on Self-Organizing Maps (MASOM) has memorized sound objects and learned how to temporally structure them by listening to large corpora of human-made music. MASOM is then able to improvise live interacting with the other (human) performers by imitating the style of what it reminds it of. For each musician, a corresponding visual agent puts its sound and musical decision into images thus allowing the audience to see who does what. This reveals the musical gestures that are so often lost in electronic music performance. For CHI, MASOM plays with two live performers for a 20 minute audiovisual REVIVE experience.
- Arne Eigenfeldt and Philippe Pasquier. 2010. Real-Time Timbral Organisation: Selecting samples based upon similarity. Organised Sound 15, 02 (Aug. 2010), 159--166. Google ScholarDigital Library
- Teuvo Kohonen. 1982. Self-organized formation of topologically correct feature maps. Biological cybernetics 43, 1 (1982), 59--69. http: //link.springer.com/article/10.1007/BF00337288Google Scholar
- Teuvo Kohonen. 1998. The self-organizing map. Neurocomputing 21, 1--3 (1998), 1--6.Google ScholarCross Ref
- Philippe Pasquier, Arne Eigenfeldt, Oliver Bown, and Shlomo Dubnov. 2017. An Introduction to Musical Metacreation. Computers in Entertainment 14, 2 (Jan. 2017), 1--14. Google ScholarDigital Library
- Ash Tanasiychuk. 2016. A Conversation with Artificial Intelligence | VANDOCUMENT. (2016). http://vandocument.com/2016/11/ a-conversation-with-artificial-intelligence/Google Scholar
- Kıvanç Tatar and Philippe Pasquier. 2017a. MASOM: A Musical Agent Architecture based on Self Organizing Maps, Affective Computing, and Variable Markov Models. In Proceedings of the 5th International Workshop on Musical Metacreation (MUME 2017). Atlanta, Georgia, USA.Google Scholar
- Kıvanç Tatar and Philippe Pasquier. 2017b. MASOM: Musical Agent based on Self-Organizing Maps. (2017). http://metacreation.net/masom/Google Scholar
Index Terms
- REVIVE: An Audio-visual Performance with Musical and Visual AI Agents
Recommendations
ImproteK: Introducing Scenarios into Human-Computer Music Improvisation
Special Issue on Musical Metacreation, Part IThis article focuses on the introduction of control, authoring, and composition in human-computer music improvisation through the description of a guided music generation model and a reactive architecture, both implemented in the software ImproteK. This ...
Stimulating Creative Partnerships in Human-Agent Musical Interaction
Special Issue on Musical Metacreation, Part IMusical duets are a type of creative partnership with a long history of artistic practice. What can they tell us about creative partnerships between a human and a computer? To explore this question, we implemented an activity-based model of duet ...
Towards a model of musical interaction and communication
In this paper we argue there is a need for a formalised description of musical interaction, which allows reasoning about the musical decisions of human and computational players. To this end, we define a simple model of musical transmission which is ...
Comments