English

Modeling Real-Time Interactive Conversations as Timed Diarized Transcripts

Machine Learning 2024-05-24 v1 Computation and Language

Abstract

Chatbots built upon language models have exploded in popularity, but they have largely been limited to synchronous, turn-by-turn dialogues. In this paper we present a simple yet general method to simulate real-time interactive conversations using pretrained text-only language models, by modeling timed diarized transcripts and decoding them with causal rejection sampling. We demonstrate the promise of this method with two case studies: instant messenger dialogues and spoken conversations, which require generation at about 30 tok/s and 20 tok/s respectively to maintain real-time interactivity. These capabilities can be added into language models using relatively little data and run on commodity hardware.

Keywords

Cite

@article{arxiv.2405.13203,
  title  = {Modeling Real-Time Interactive Conversations as Timed Diarized Transcripts},
  author = {Garrett Tanzer and Gustaf Ahdritz and Luke Melas-Kyriazi},
  journal= {arXiv preprint arXiv:2405.13203},
  year   = {2024}
}

Comments

GT and GA contributed equally

R2 v1 2026-06-28T16:34:57.492Z