Pith. sign in

REVIEW 3 cited by

TurnGPT: a Transformer-based Language Model for Predicting Turn-taking in Spoken Dialog

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2010.10874 v1 pith:2S7IWLGK submitted 2020-10-21 cs.CL cs.AI

Erik Ekstedt , Gabriel Skantze This is my paper · ORCID
classification cs.CLcs.AI
keywords modeldialogturn-takingspokencompletenesslanguagepragmaticpredicting
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Syntactic and pragmatic completeness is known to be important for turn-taking prediction, but so far machine learning models of turn-taking have used such linguistic information in a limited way. In this paper, we introduce TurnGPT, a transformer-based language model for predicting turn-shifts in spoken dialog. The model has been trained and evaluated on a variety of written and spoken dialog datasets. We show that the model outperforms two baselines used in prior work. We also report on an ablation study, as well as attention and gradient analyses, which show that the model is able to utilize the dialog context and pragmatic completeness for turn-taking prediction. Finally, we explore the model's potential in not only detecting, but also projecting, turn-completions.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 3 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. FireRedChat: A Pluggable, Full-Duplex Voice Interaction System with Cascaded and Semi-Cascaded Implementations

    cs.SD 2025-09 conditional novelty 5.0 of 10

    A full-duplex voice system with streaming personalized VAD and semantic end-of-turn detection reports fewer false barge-ins and latencies near commercial benchmarks.

  2. Amplifying Minority Voices: AI-Mediated Devil's Advocate System for Inclusive Group Decision-Making

    cs.HC 2025-02 conditional novelty 4.0 of 10

    An LLM-powered devil's advocate that paraphrases minority members' private dissents as its own messages could reduce social pressure and increase opinion diversity in group decisions, but the paper provides no user st...

  3. Multimodal Transformer Models for Turn-taking Prediction: Effects on Conversational Dynamics of Human-Agent Interaction during Cooperative Gameplay

    cs.HC 2025-02 conditional novelty 4.0 of 10

    A crossmodal transformer predicts turn-taking in human-agent game dialogue with 87.3% accuracy, but a 60-person user study shows no significant perception improvements and mixed interruption effects.

Pith tools