English

Robo Sapiens

Other Computer Science 2023-10-13 v1

Abstract

This paper proposes a new method of natural language acquisition for robots that does not require the conversion of speech to text. Folks'Talks employs voice2voice technology that enables a robot to understand the meaning of what it is told and to have the ability to learn and understand new languages - inclusive of accent, dialect, and physiological differences. To do this, sound processing and computer vision are incorporated to give the robot a sense of spatiotemporal causality. The "language model" we are proposing equips a robot to imitate a natural speaker's conversational behavior by thinking contextually and articulating its surroundings.

Keywords

Cite

@article{arxiv.2310.08323,
  title  = {Robo Sapiens},
  author = {Chaim Ash and Amelia Hans},
  journal= {arXiv preprint arXiv:2310.08323},
  year   = {2023}
}
R2 v1 2026-06-28T12:48:42.187Z