Behavior-Based Early Language Development on a Humanoid Robot

Abstract

We are exploring the idea that early language acquisition could be better modelled on an artificial creature by considering the pragmatic aspect of natural language and of its development in human infants. We have implemented a system of vocal behaviors on Kismet in which "words" or concepts are behaviors in a competitive hierarchy. This paper reports on the framework, the vocal system's architecture and algorithms, and some preliminary results from vocal label learning and concept formation.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Jan 01, 2002
Accession Number
ADA434707

Entities

People

  • Paulina Varshavskaya

Organizations

  • Massachusetts Institute of Technology

Tags

DTIC Thesaurus Topics

  • Acquisition
  • Algorithms
  • Artificial Intelligence
  • Artificial Intelligence Software
  • Autonomous Agents
  • Competition
  • Computational Science
  • Control Systems
  • Environment
  • Grammars
  • Language
  • Linguistics
  • Machines
  • Natural Languages
  • Recognition
  • Robotics
  • Speech

Readers

  • Agent-Based Social Robotics and Mobile-Assisted Learning in Virtual Environments.
  • Artificial Intelligence
  • Speech Processing/Speech Recognition.

Technology Areas

  • AI & ML
  • AI & ML - Machine Translation
  • Autonomy