Chatterbox: an interactive system of gibberish agents
Paper in proceeding, 2020

We present the interactive multi-agent system Chatterbox, as part of the sound art installation Translanguaging, exploring the notion of translanguaging as a mediation of multilingual and intercultural communication. We discuss the act of languaging as a dual process comprising both semantic language communication, as well as paralanguage that relates to the affective, personal, and cultural aspects related to translanguaging. Through the creation of the Chatterbox agent, generating gibberish vocal streams devoid of semantic content, we aim at highlighting the paralinguistic dimension of languaging. The agent model comprises a kind of gradient map, clustering a segmented corpus of vocal sounds in the latent space of a self-organized map, according to its paralinguistic fingerprint. We utilize Factor Oracles for the creative generation of novel utterances of paralanguaging gibberish by the agent. Incorporating simple subsumption architecture inspired rules, we further moderate the interaction between the gibberish agents, creating rich and complex multi-agent behavior in “paralanguaging discussion”. We outline the artistic and technical considerations in developing our Chatterbox agent throughout the paper. We share several observations made throughout the process of creating the Chatterbox agent, highlighting some of the connections between the notion of (trans)languaging and the implementation of our model.

sound and music computing

multiagent systems

machine learning

sound art

musical agents

Author

Ronald Boersen

Simon Fraser University

Aaron Liu-Rosenbaum

Universite Laval

Kivanc Tatar

Data Science and AI

Philippe Pasquier

Simon Fraser University

Proceedings of 26th International Symposium of Electronic Arts (ISEA 2020)


978-2-9816413-2-8 (ISBN)

International Symposium of Electronic Arts (ISEA 2020)
Montreal, Canada,

Subject Categories

Media and Communication Technology

More information

Latest update

2/20/2024