Modeling turn-taking with distant viewing: investigating silence thresholds in human and AI-generated discourse

Taylor Arnold; Nicolas Ballier; Artem Saloev

Modeling turn-taking with distant viewing: investigating silence thresholds in human and AI-generated discourse

Computation and Language 2026-07-20 v1

Authors: Taylor Arnold , Nicolas Ballier , Artem Saloev

Abstract

This study investigates silence gaps in two kinds of audiovisual material. We analysed thirty US situational comedies and fifty-one synthetic podcasts generated with Google NotebookLM. Gaps were compared across speaker gender, assigned from a fundamental-frequency threshold estimated in Praat, and across production settings.

Keywords

turn-taking silence gaps discourse analysis AI-generated content gender fundamental frequency

Cite

@article{arxiv.2607.18076,
  title  = {Modeling turn-taking with distant viewing: investigating silence thresholds in human and AI-generated discourse},
  author = {Taylor Arnold and Nicolas Ballier and Artem Saloev},
  journal= {arXiv preprint arXiv:2607.18076},
  year   = {2026}
}

Comments

10 pages, MeSSH26 (Méthodes pour les sciences sociales et les humanités - Methods for social sciences and humanities 2026)