TurnFSM for Full-Duplex Dialogue System: Internalizing State-Machine Logic for Streaming Semantic Voice Activity Detection and Utterance-Level Rejection
Full-duplex voice assistants must continuously listen while speaking, handling user interruptions under low-latency and resource-constrained streaming conditions. Existing end-to-end full-duplex models can compromise reasoning-related capabilities after speech-domain adaptation, whereas cascaded pipelines introduce ext...