Data to 14 Oct 2026

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

arXiv 2010.10874 ↗First posted 21 Oct 2020cs.CL cs.AIcited by 56

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. Cited by 56 papers in the map (data through 14 Oct 2026). First posted on arXiv 21 Oct 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 4; 2023: 3; 2024: 8; 2025: 17; 2026: 24.

56 papers.

Sort:

By area:

2022Generative Spoken Dialogue Language Modelingcited by 126
2025On The Landscape of Spoken Language Models: A Comprehensive Surveycited by 118
2024WavChat: A Survey of Spoken Dialogue Modelscited by 90
2025Talking Turns: Benchmarking Audio Foundation Models on Turn-Taking Dynamicscited by 47
2023Transformers in Speech Processing: A Surveycited by 39
2024Proactive Conversational Agents with Inner Thoughtscited by 36
2022Duplex Conversation: Towards Human-like Interaction in Spoken Dialogue Systemscited by 28
2024Multilingual Turn-taking Prediction Using Voice Activity Projectioncited by 26
2024Real-time and Continuous Turn-taking Prediction Using Voice Activity Projectioncited by 21
2024Turn-taking and Backchannel Prediction with Acoustic and Large Language Model Fusioncited by 20
2025FlexDuo: A Pluggable System for Enabling Full-Duplex Capabilities in Speech Dialogue Systemscited by 15
2025Applying General Turn-taking Models to Conversational Human-Robot Interactioncited by 13

38 more

2024Large Language Models Know What To Say But Not When To Speakcited by 11
2025Predicting Turn-Taking and Backchannel in Human-Machine Conversations Using Linguistic, Acoustic, and Visual Signalscited by 10
2022When can I Speak? Predicting initiation points for spoken dialogue agentscited by 9
2022Gated Multimodal Fusion with Contrastive Learning for Turn-taking Prediction in Human-robot Dialoguecited by 8
2025A Noise-Robust Turn-Taking System for Real-World Dialogue Robots: A Field Experimentcited by 6
2025Speculative End-Turn Detector for Efficient Speech Chatbot Assistantcited by 6
2025Time to Talk: LLM Agents for Asynchronous Group Communication in Mafia Gamescited by 6
2025Chain-of-Thought Reasoning in Streaming Full-Duplex End-to-End Spoken Dialogue Systemscited by 5
2026Optimizing Conversational Quality in Spoken Dialogue Systems with Reinforcement Learning from AI Feedbackcited by 5
2026Speak or Stay Silent: Context-Aware Turn-Taking in Multi-Party Dialoguecited by 5
2023Attribution and Alignment: Effects of Local Context Repetition on Utterance Production and Comprehension in Dialoguecited by 4
2025Conversational Agents as Catalysts for Critical Thinking: Challenging Social Influence in Group Decision-makingcited by 4
2025Beyond Words: Multimodal LLM Knows When to Speakcited by 4
2026DualTurn: Learning Turn-Taking from Dual-Channel Generative Speech Pretrainingcited by 4
2023Response-conditioned Turn-taking Predictioncited by 3
2024Predictive Speech Recognition and End-of-Utterance Detection Towards Spoken Dialog Systemscited by 2
2025Prior Lessons of Incremental Dialogue and Robot Action Management for the Age of Language Modelscited by 2
2025Thai Semantic End-of-Turn Detection for Real-Time Voice Agentscited by 2
2025Multimodal Transformer Models for Turn-taking Prediction: Effects on Conversational Dynamics of Human-Agent Interaction during Cooperative Gameplaycited by 1
2025Prompt-Guided Turn-Taking Predictioncited by 1
2025Investigating the Representation of Backchannels and Fillers in Fine-tuned Language Modelscited by 1
2025Modeling Turn-Taking with Semantically Informed Gesturescited by 1
2026Syn-TurnTurk: A Synthetic Dataset for Turn-Taking Prediction in Turkish Dialoguescited by 1
2026Aligning Backchannel and Dialogue Context Representations via Contrastive LLM Fine-Tuningcited by 1
2026When2Speak: A Dataset for Temporal Participation and Turn-Taking in Multi-Party Conversations for Large Language Modelscited by 1
2026TurnNat: Automatic Evaluation of Turn-Taking Naturalness in Dyadic Spoken Dialoguecited by 1
2026DuplexGen: Adaptive Synthesis of Human-AI Turn-Taking Dialoguescited by 1
2026Multi-turn Conversational AI from Text to Multimodal Interaction: Data, Models, Evaluation, and Open Challengescited by 1
2026Full-Duplex Speech Models Take the Floor When Asked, Not When Neededcited by 1
2024Detecting the terminality of speech-turn boundary for spoken interactions in French TV and Radio contentcited by 0
2026UAF: A Unified Audio Front-end LLM for Full-Duplex Speech Interactioncited by 0
2026Evaluating Large Language Models Abilities for Addressee, Turn-change, and Next Speaker Prediction in Meetingscited by 0
2026Low-Latency Turn-Taking via Context-Aware Preface Generation in a Real-World Dialogue Robotcited by 0
2026Latent-IM: Latent Interaction Management for Speech LLMscited by 0
2026CallScreenBench: Benchmarking Small Language Models as Phone Secretariescited by 0
2026TIDES: A Longitudinal Bilingual Dataset for Modeling Multi-Party Social Dynamicscited by 0
2026Conversation Coach: A Voice-enabled AI System that Helps Practice Difficult Workplace Conversationscited by 0
2026Decoupling Turn-Taking from Semantics: A Decoupled Data Approach for Finite-State-Machine-Based Full-Duplex Dialoguecited by 0

50 most cited of 56 All 56 (JSON)