XTurnix: Large-Scale Self-Supervised Turn Control through Two-State Binary Decisions

Excerpt

arXiv:2610.04400v1 Announce Type: cross 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