Abstract
General turn-taking behavior in real-time dialogue systems requires deciding whether to keep listening or start responding while listening, and whether to continue or stop while speaking. Existing turn detectors use heterogeneous, task-specific label spaces and are often trained on limited annotations or evaluated on isolated utterances, making them difficult to use as a unified causal controller with comprehensive context. We propose XTurnix, a compact text-based model that formulates turn control as two binary decisions conditioned on the AI's current listening or speaking state and predicts a single control token from the complete dialogue history. XTurnix is pretrained on 5.5 million causal action examples automatically derived from timestamped two-speaker transcripts, then fine-tuned on synthetic multi-turn examples with a flatter distribution across the four state-action labels. We evaluate XTurnix on four public benchmarks and a balanced self-curated benchmark. Across the public benchmarks, XTurnix achieves the best results on all SemanticVAD and LiveKit splits, ties the native Smart-Turn model on Smart-Turn Bench, and achieves the highest incomplete-turn accuracy on Easy-Turn. On the self-curated benchmark, it reaches 89.06% accuracy, more than 20 percentage points above the strongest third-party baseline at 68.75%, while maintaining F1 scores between 84.21% and 90.63% across all four categories. These results demonstrate unified listening- and speaking-state turn control in a single compact model. Code is available at https://github.com/xcc-zach/xturnix, with an interactive demo at https://huggingface.co/spaces/xcczach/xturnix-demo.
Keywords
Subject
Publication details
- Journal
- Not available
- Open access
- Green open access
Cite this article
APA 7
Liu, Z., Duan, Y., Wu, H., Yang, C., Cheng, Q., Wang, K., Zeng, X., Qiu, X., Lu, C., & Chen, X. (2026). XTurnix: Large-Scale Self-Supervised Turn Control through Two-State Binary Decisions. https://omanscience.com/en/articles/xturnix-large-scale-self-supervised-turn-control-through-two-state-binary-decisions
MLA 9
Liu, Zhanxun, et al. "XTurnix: Large-Scale Self-Supervised Turn Control through Two-State Binary Decisions." https://omanscience.com/en/articles/xturnix-large-scale-self-supervised-turn-control-through-two-state-binary-decisions.
Chicago (author–date)
Liu, Zhanxun, Yifan Duan, Hengtao Wu, Chen Yang, Qinyuan Cheng, Kun Wang, Xingyu Zeng, Xipeng Qiu, Chaochao Lu, and Xie Chen. 2026. "XTurnix: Large-Scale Self-Supervised Turn Control through Two-State Binary Decisions." https://omanscience.com/en/articles/xturnix-large-scale-self-supervised-turn-control-through-two-state-binary-decisions.
Harvard
Liu, Z., Duan, Y., Wu, H., Yang, C., Cheng, Q., Wang, K., Zeng, X., Qiu, X., Lu, C. and Chen, X. (2026) 'XTurnix: Large-Scale Self-Supervised Turn Control through Two-State Binary Decisions', Available at: https://omanscience.com/en/articles/xturnix-large-scale-self-supervised-turn-control-through-two-state-binary-decisions.
Vancouver
Liu Z, Duan Y, Wu H, Yang C, Cheng Q, Wang K, et al. XTurnix: Large-Scale Self-Supervised Turn Control through Two-State Binary Decisions. https://omanscience.com/en/articles/xturnix-large-scale-self-supervised-turn-control-through-two-state-binary-decisions
IEEE
Z. Liu, Y. Duan, H. Wu, C. Yang, Q. Cheng, K. Wang, X. Zeng, X. Qiu, C. Lu, and X. Chen, "XTurnix: Large-Scale Self-Supervised Turn Control through Two-State Binary Decisions," https://omanscience.com/en/articles/xturnix-large-scale-self-supervised-turn-control-through-two-state-binary-decisions.